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-INT4Qwen3.6-35B-A3B-GPTQ-Int4Qwen3.8-27B-BF16-INT4-W4A16-G32-AutoRoundQwen3.8-27B-GPTQ-Int4Qwen3.6-27B-GPTQ-Int4Apodex-1.1-mini-GPTQ-Int4GLM-5.3-Flash-AWQ-INT4Qwen3.8-27B-int4-g128-sym-autoroundQwen3.8-27B-AWQ-INT4-MTP-LowLatencyQwen3.8-27B-DavidAU-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU-INT4-W4A16Qwen3.8-27B-INT4-W4A16Qwen3.8-27B-BF16-INT4-W4A16-G32-AutoRound-v2Qwen3.5-4B-AX650-GPTQ-Int4-C512-P30k-CTX32kKAT-Coder-V2.5-Dev-AWQ-INT4Qwopus3.8-27B-Flash-INT4-W4A16Swift-Qwen3.8-27B-Uncensored-GPTQ-Int4-sym-G128-MTP-BF16GLM-5.3-Flash-colibri-int4-g64Qwen3.8-9B-gptq-int4Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GPTQ-int4Qwen2.5-VL-3B-Instruct-GPTQ-Int4gemma-3-12b-it-AWQ-INT4Qwen2-VL-2B-Instruct-GPTQ-Int4Qwen3.6-27b-gptq-int4Qwen2-VL-7B-Instruct-GPTQ-Int4Qwen2.5-VL-7B-Instruct-GPTQ-Int4gemma-3-27b-it-AWQ-INT4Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-GPTQ-Int4Qwen3.8-27B-int4-AutoRound-SARQwen3.6-35B-A3B-GPTQ-INT4-W4A16-LowLatencyQwen3-VL-2B-Instruct-GPTQ-Int4
