models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3.8-27B-W4A16-AutoRound-GPTQgemma-4-E4B-it-W4A16-AutoRound-GPTQQwen3.5-9B-W4A16-AutoRound-GPTQLlama-3.3-70B-Instruct-AutoRound-GPTQ-4bitQwen3.8-9B-Distill-W4A16-AutoRound-GPTQMistral-Small-3.1-24B-Instruct-2503-int4-AutoRound-gptq-symgemma-4-E2B-it-W4A16-AutoRound-GPTQDeepSeek-R1-Distill-Qwen-7B-AutoRound-GPTQ-4bitgemma-4-12B-it-W4A16-AutoRound-GPTQOLMo-2-1124-7B-Instruct-AutoRound-GPTQ-4bitMistral-Small-3.2-24B-Instruct-2506-GPTQ-AutoRound-TextOnlyIFM-K2-Horizon-MoVA-36B-A4B-W4A16-AutoRound-GPTQMuse-Glimmer-30B-W4A16-AutoRound-GPTQdots.mocr-W4A16-AutoRound-GPTQQwen3.5-0.8B-W4A16-AutoRound-GPTQQwen3.8-2B-Distill-W4A16-AutoRound-GPTQMicrosoft-phi-4-Instruct-AutoRound-GPTQ-4bitQwen3.5-4B-W4A16-AutoRound-GPTQllama-joycaption-beta-one-hf-llava-GPTQ-4bit-sym-autoroundPhi-4-AutoRound-GPTQ-4bitQwen3.5-2B-W4A16-AutoRound-GPTQQwen3.8-4B-Distill-W4A16-AutoRound-GPTQQwen3-32B-autoround-2bit-gptqmeta-llama_Llama-3.2-1B-Instruct-auto_gptq-int4-gs128-symNuExtract3-W4A16-AutoRound-GPTQQwen3.5-4B-W4A16-AutoRound-GPTQQwen3-8B-autoround-4bit-gptqQwen3-VL-8B-Instruct-W4A16-AutoRound-GPTQQwen3.8-27B-W4A16-g64-AutoRound-GPTQQwen3.5-2B-W4A16-AutoRound-GPTQ
