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-Embedding-0.6B-4bit-DWQQwen3-Embedding-4B-4bit-DWQQwen3-Coder-30B-A3B-Instruct-6bit-DWQ-lr3e-7Qwen3-Embedding-8B-4bit-DWQQwen3-4B-Instruct-2507-4bit-DWQ-2510Qwen3-Coder-30B-A3B-Instruct-4bit-dwq-v2Kimi-Dev-72B-4bit-DWQQwen3.6-35B-A3B-4bit-DWQQwen3-Coder-30B-A3B-Instruct-4bit-DWQgemma-3-1b-it-4bit-DWQLing-2.6-flash-mlx-4bit-DWQApertus-v1.5-8B-text-MLX-4bit-DWQDolphin-Mistral-24B-Venice-Edition-DWQQwen3-30B-A3B-4bit-DWQQwen3-14B-4bit-DWQ-053125Qwen3-1.7B-4bit-DWQ-053125Qwen3.5-9B-OmniCoder-Claude-Polaris-Text-dwq4-mlxQwen3-Embedding-8B-4bit-DWQQwen3-1.7B-4bit-DWQLlama-3.3-70B-Instruct-4bit-DWQQwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr5e-8Qwen3.8-27B-oQ4e-DWQ-MTP-MLXHuihui-Qwen3-30B-A3B-Instruct-2507-abliterated-dwq4-mlxgemma-3n-E2B-it-text-4bit-dwqQwen3-Coder-30B-A3B-Instruct-8bit-DWQ-lr9e8Qwen3.5-9B-Claude-GBO-Fire-Deckard-Agent-Heretic-dwq4-mlxgemma-3-4b-it-4bit-DWQgemma-4-26B-A4B-it-4bit-DWQDevstral-Small-2507-4bit-DWQGranite-4.0-H-Tiny-4bit-DWQ