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.
Qwen3.6-35B-A3B-GPTQ-Int4Qwen3.8-27B-GPTQ-Int4-sym-G128-MTP-BF16Qwen3.8-27B-GPTQ-Int4Qwen3.6-27B-GPTQ-Int4c4ai-command-r-plus-GPTQApodex-1.1-mini-GPTQ-Int4MiniCPM5-2B-GPTQQwen3.8-27B-Uncensored-GPTQ-Int4-sym-G128-MTP-BF16Qwen3.5-4B-AX650-GPTQ-Int4-C512-P30k-CTX32kMiniCPM4.1-8B-GPTQQwen3-Coder-Next-GPTQQwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GPTQ-int4Swift-Qwen3.8-27B-Uncensored-GPTQ-Int4-sym-G128-MTP-BF16Qwen3-VL-4B-Instruct-GPTQ-W4A16Qwen2.5-VL-3B-Instruct-GPTQ-Int4Qwen3.6-27b-gptq-int4Baichuan-M3-235B-GPTQ-INT4Qwen2.5-VL-7B-Instruct-GPTQ-Int4Qwen3-Coder-Next-GPTQDeepSeek-OCR-2-GPTQ-INT8Qwen-7B-Chat-GPTQQwen3-VL-2B-Instruct-GPTQ-Int4Qwen3.8-27B-W4A16-g128-sym-GPTQHY-MT1.5-1.8B-GPTQ-Int4Qwen3.6-35B-A3B-GPTQ-INT4-W4A16-LowLatencyHuihui-Qwen3.8-27B-abliterated-GPTQ-Int4-sym-G128-MTP-BF16-B70GLM-4.7-Flash-GPTQ-4bitBaichuan-M2-32B-GPTQ-Int4Ovis2-4B-GPTQ-Int4granite-4.2-8b-2bit-gptq-mlx
