Qwen3-8B-QAT-INT4

422
1
8.0B
license:apache-2.0
by
pytorch
Language Model
OTHER
8B params
New
422 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
18GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
8GB+ RAM

Code Examples

Inference with vLLMtextvllm
pip install --pre vllm --extra-index-url https://wheels.vllm.ai/nightly
pip install --pre torchao torch --index-url https://download.pytorch.org/whl/nightly/cu128
Inference with vLLMtextvllm
pip install --pre vllm --extra-index-url https://wheels.vllm.ai/nightly
pip install --pre torchao torch --index-url https://download.pytorch.org/whl/nightly/cu128
Servingbashvllm
# Server
export MODEL=pytorch/Qwen3-8B-QAT-INT4
VLLM_DISABLE_COMPILE_CACHE=1 vllm serve $MODEL --tokenizer $MODEL -O3
Servingbashvllm
# Server
export MODEL=pytorch/Qwen3-8B-QAT-INT4
VLLM_DISABLE_COMPILE_CACHE=1 vllm serve $MODEL --tokenizer $MODEL -O3
Inference with Transformersbash
pip install git+https://github.com/huggingface/transformers@main
pip install --pre torchao torch --index-url https://download.pytorch.org/whl/nightly/cu128
pip install accelerate
Inference with Transformersbash
pip install git+https://github.com/huggingface/transformers@main
pip install --pre torchao torch --index-url https://download.pytorch.org/whl/nightly/cu128
pip install accelerate
baselinebash
lm_eval --model hf --model_args pretrained=Qwen/Qwen3-8B --tasks mmlu --device cuda:0 --batch_size auto
baselinebash
lm_eval --model hf --model_args pretrained=Qwen/Qwen3-8B --tasks mmlu --device cuda:0 --batch_size auto
Setupbashvllm
git clone [email protected]:vllm-project/vllm.git
Setupbashvllm
git clone [email protected]:vllm-project/vllm.git
Setuptextvllm
VLLM_USE_PRECOMPILED=1 pip install --editable .
Setuptextvllm
VLLM_USE_PRECOMPILED=1 pip install --editable .
benchmark_latencybashvllm
vllm bench latency --input-len 256 --output-len 256 --model Qwen/Qwen3-8B --batch-size 1
benchmark_latencybashvllm
vllm bench latency --input-len 256 --output-len 256 --model Qwen/Qwen3-8B --batch-size 1

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.