GLM-4.5-Air-GPTQ-Int4-Int8Mix

Name: GLM-4.5-Air-GPTQ-Int4-Int8Mix
Author: QuantTrio

4.9K

—

QuantTrio

Language Model

OTHER

New

5K downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

AI model with specialized capabilities.

Code Examples

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

textvllm

CONTEXT_LENGTH=32768

VLLM_USE_MODELSCOPE=true vllm serve \
    QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --served-model-name GLM-4.5-Air-GPTQ-Int4-Int8Mix \
    --enable-expert-parallel \
    --swap-space 16 \
    --max-num-seqs 512 \
    --max-model-len $CONTEXT_LENGTH \
    --max-seq-len-to-capture $CONTEXT_LENGTH \
    --gpu-memory-utilization 0.9 \
    --tensor-parallel-size 8 \
    --trust-remote-code \
    --disable-log-requests \
    --host 0.0.0.0 \
    --port 8000

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

【Model Files】python

from huggingface_hub import snapshot_download
  snapshot_download('QuantTrio/GLM-4.5-Air-GPTQ-Int4-Int8Mix', cache_dir="your_local_path")

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.