GLM-4.5-Air-REAP-82B-A12B

2.4K
87
82.0B
2 languages
license:mit
by
cerebras
Language Model
OTHER
82B params
New
2K downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
184GB+ RAM
Mobile
Laptop
Server
Quick Summary

๐“Œณ REAP ๐“Œณ the Experts: Why Pruning Prevails for One-Shot MoE Compression Introducing GLM-4.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
77GB+ RAM

Code Examples

๐Ÿš€ Deploymentbashvllm
vllm serve cerebras/GLM-4.5-Air-REAP-82B-A12B \
    --tensor-parallel-size 4 \
    --tool-call-parser glm45 \
    --enable-auto-tool-choice \
    --enable-expert-parallel

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.