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-Coder-30B-A3B-Instruct-MLX-6bitQwen3-4B-Instruct-2507-MLX-6bitQwen3-4B-Thinking-2507-MLX-6bitQwen3-8B-64k-Context-2X-Josiefied-UncensoredQwen3.8-Whittle-MoE-27B-A17.8B-GGUFQwen3-30B-A3B-Instruct-2507-MLX-6bitQwen3.8-Flash-Next-131B-A6B-GGUFQwen3.8-Flash-Next-REAM-60Pct-GGUFQwen3-Next-80B-A3B-Instruct-MLX-6bitQwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-IQ4_XS-GGUFQwen3-14B-GGUFQwen3-Coder-480B-A35B-Instruct-MLX-6bitQwen3-6B-Hivemind-Instruct-Heretic-Abliterated-Uncensored-NEO-Imatrix-GGUFHuihui-Qwen3.5-9B-abliterated-GPTQ-Pro-4bit-g64Qwen3-Coder-30B-A3B-Instruct-6bit-DWQ-lr3e-7Qwen3.5-397B-A17B-Opus-4.6-Reasoning-Uncensored-GGUFQwen3.8-27B-heretic-ara-Q6_K-GGUFQwen3.8-27B-Abliterated-IQ4-MIX-MTP-GGUFQwen3-8B-64k-Josiefied-Uncensored-NEO-Max-GGUFQwen3-8B-hereticQwen3.5-0.8B-hereticQwen3-235B-A22B-Instruct-2507-MLX-6bitQwen3.8-Whittle-16BQwen3.8-Whittle-Next-19.8B-A10B-baseQwen3.5-2B-hereticQwen3.8-Flash-Next-tq4a-tq2e-g64Qwen3.8-27B-Heretic-Uncensored-Q6_K-GGUFQwen3-0.6B-hereticQwen3.8-27B-MTPLX-Optimized-Speed-M3Max-Q4G64Qwen3-1.7B-heretic