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.
Apriel-1.6-15b-ThinkerQwen3.8-Flash-Next-Uncensored-MLX-Serve-4bitApriel-1.5-15b-ThinkerQwen3.8-Flash-Next-Uncensored-MLX-Serve-mixed-4-8bitServiceNow-AI_Apriel-1.6-15b-Thinker-GGUFQwen3.8-27B-MLX-Serve-4bitQwen3.8-Flash-Next-REAP-288-MLX-Serve-4bit-MTPServiceNow-AI_Apriel-1.5-15b-Thinker-GGUFOrnith-1.5-35B-A3B-GPTQ-Int4-sym-G128-MTP-BF16-MixedCal-v2Qwen3.8-Flash-Next-Uncensored-MLX-Serve-mixed-3-8bitOrnith-1.5-35B-A3B-AutoRound-W4A16-sym-G128-MTP-BF16Qwen3.8-27B-MLX-Serve-8bitQwen3-VL-32B-Thinking-heretic-GGUFKimi-K2.7-Code-GGUFMiMo-V2.6-Distill-Qwen-9B-MLX-Serve-6bitsmall-testMiMo-V2.6-Distill-Qwen-9B-MLX-Serve-8bitSuperApriel-15B-InstructGroundNext-7B-V0serbian-emotion-qwen3.5-9bQwen3-VL-8B-Instruct-heretic-ggufQwen3.8-Flash-Next-mixed-6-8-ple8-mlx-serveMiMo-V2.6-Distill-Qwen-9B-MLX-Serve-4bitStarless-Seraph-31BQwythos-9B-Claude-Mythos-5-1M-GGUFSuperApriel-15b-Basehome-servicesGLM-5.3-FlashQwen3.8-27B-int4-gdn8-ovgemma-3-isv-gpt-v15-merged
