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-AutoRoundQwen3.8-27B-Uncensored-W4A16-AutoRoundQwen3.8-27B-BF16-INT4-W4A16-G32-AutoRoundQwen3.8-27B-W4A16-AutoRoundgemma-4-E4B-it-W4A16-AutoRound-GPTQQwen3.8-27B-int4-g128-sym-autoroundGLM-5.3-Flash-W4A16-AutoRoundQwen3.8-27B-BF16-INT4-W4A16-G32-AutoRound-v2Qwen3.8-27B-NVFP4-AutoRoundMiniMax-M2.7-REAP-172B-A10B-AutoRound-W4A16Huihui-Qwen3.8-27B-Abliterated-W4A16-AutoRoundQwen3.6-40B-Fable-Fusion-6-Core-Deckard-Eleanor-Heretic-Uncensored-W4A16-AutoRoundLlama-3.3-70B-Instruct-AutoRound-GPTQ-4bitQwen3.8-27B-W4A16-AutoRound-INT8-Head-EmbeddingsQwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-W4A16-AutoRoundGLM-5.3-Flash-MXFP4-Mixed-CT-AutoRoundQwen3.8-27B-int4-AutoRound-SARGLM-5.1-MXFP4-Mixed-CT-AutoRoundQwen3.5-122B-A10B-heretic-int4-AutoRoundOrnith-1.0-35B-int4-AutoRoundGLM-5.3-Flash-W4A16-RTN-AutoRoundHuihui-Qwen3.6-35B-A3B-abliterated-int4-AutoRoundQwen3.8-27B-W4A16-AutoRound-fast-ruQwen3.5-397B-A17B-heretic-int4-AutoRoundgemma-4-E2B-it-W4A16-AutoRoundLFM2.5-2.6B-AutoRound-W8A16gemma-4-E2B-it-W4A16-AutoRound-GPTQDeepSeek-R1-Distill-Qwen-7B-AutoRound-GPTQ-4bitQwen3.8-27B-W4A16-AutoRoundNVIDIA-Nemotron-3.5-Lightning-30B-A3B-INT4-AutoRound
