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-AWQ-4bitmistral-7b-v0.3-bnb-4bitQwen2.5-Coder-7B-Instruct-4bitDeepSeek-R1-0528-Qwen3-8B-MLX-4bitOrnith-1.5-9B-MLX-4bitQwen2.5-14B-bnb-4bitQwen3-30B-A3B-Instruct-2507-AWQ-4bitOrnith-1.5-35B-A3B-MLX-4bitQwen3-8B-4bitQwen3-14B-unsloth-bnb-4bitQwen3-Coder-30B-A3B-Instruct-MLX-4bitLing-3.0-tiny-MLX-4bitQwen3-4B-Instruct-2507-unsloth-bnb-4bitQwen2.5-7B-Instruct-bnb-4bitQwen2.5-Coder-14B-Instruct-MLX-4bitllama-3-8b-Instruct-bnb-4bitQwen2.5-Math-7B-4bitQwen2.5-3B-Instruct-unsloth-bnb-4bitLFM2-24B-A2B-MLX-4bitMLX-Qwopus3.5-9B-v3-4bitLFM2.5-1.2B-Instruct-MLX-4bitgpt-oss-20b-unsloth-bnb-4bitQwen3-14B-MLX-4bitQwen2.5-Coder-7B-Instruct-bnb-4bitQwen2.5-7B-Instruct-unsloth-bnb-4bitMeta-Llama-3.1-8B-Instruct-bnb-4bitQwen3.6-27B-AWQ-4bitQwen3-8B-MLX-4bitQwen2.5-0.5B-Instruct-4bitQwen3-1.7B-unsloth-bnb-4bit
