meta-llama

/

Llama-3.2-3B-Instruct

like 644

Follow

Meta Llama 8,815

I am happy to announce that users that want even faster inference of Llama 3.2 3B Instruct with even lower vram requirements can now production deploy via vLLM/SGLang using our highly accurate gptq 4bit quantized model

https://x.com/ModelCloudAi/status/1852249758913724752
https://huggingface.co/ModelCloud/Llama-3.2-3B-Instruct-gptqmodel-4bit-vortext-v3