Llama-3.2-1B-Instruct GPTQ Quantized
Collection
GPTQ quantized across W4A16, W8A8, FP8, NVFP4 using llm-compressor. • 4 items • Updated
Quantized Models
Bunch of good models
-
-
soyrsoyr/Qwen3.8-27B-W4A16-AWQ-GPTQ
Image-Text-to-Text • 11B • Updated • 18.4k • 7 -
soyrsoyr/Qwen3.6-27B-W4A16-AWQ-GPTQ
Text Generation • 27B • Updated • 75 -
soyrsoyr/Qwen3.6-27B-FP8-dynamic
Image-Text-to-Text • 27B • Updated • 19 -
soyrsoyr/Muse-Glimmer-30B-NVFP4
Image-Text-to-Text • 19B • Updated • 78 -
soyrsoyr/Muse-Glimmer-30B-W4A16-AWQ-GPTQ
Image-Text-to-Text • 8B • Updated • 274 -
soyrsoyr/Muse-Glimmer-30B-FP8-dynamic
Image-Text-to-Text • 30B • Updated • 71 -
soyrsoyr/Qwen3.8-27B-FP8-dynamic
27B • Updated • 122 -
soyrsoyr/gemma-4-12b-it-W4A16-GPTQ
13B • Updated • 374 -
soyrsoyr/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-MTP
Text Generation • 17B • Updated • 396 -
soyrsoyr/deepseek-moe-16b-chat-W4A16-GPTQ
Text Generation • 3B • Updated • 74