GPTQ DeepCompressor GPTQ models for nn.Linear 4bit weight & 16bit activation (symmetric) integer quantization karamjotsingh/Qwen2.5-3B-Instruct Updated Mar 12 karamjotsingh/Qwen2.5-VL-3B-Instruct Updated Apr 9 karamjotsingh/Llama-3.2-1B-Instruct Updated Apr 27 karamjotsingh/Qwen3-VL-4B-Instruct Updated Apr 23
AWQ RQP RQP AWQ models with int4 asymmetric integer weight-only quantization karamjotsingh/Qwen3-4B-Base Updated Mar 17 karamjotsingh/Llama-2-7b-chat-hf Updated Feb 19 karamjotsingh/Llama-3.2-3B-Instruct Updated Jul 8 karamjotsingh/gemma-3-4b-it Updated Dec 9, 2025
GPTQ DeepCompressor GPTQ models for nn.Linear 4bit weight & 16bit activation (symmetric) integer quantization karamjotsingh/Qwen2.5-3B-Instruct Updated Mar 12 karamjotsingh/Qwen2.5-VL-3B-Instruct Updated Apr 9 karamjotsingh/Llama-3.2-1B-Instruct Updated Apr 27 karamjotsingh/Qwen3-VL-4B-Instruct Updated Apr 23
AWQ RQP RQP AWQ models with int4 asymmetric integer weight-only quantization karamjotsingh/Qwen3-4B-Base Updated Mar 17 karamjotsingh/Llama-2-7b-chat-hf Updated Feb 19 karamjotsingh/Llama-3.2-3B-Instruct Updated Jul 8 karamjotsingh/gemma-3-4b-it Updated Dec 9, 2025
