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-MLX-4bitgemma-4-26B-A4B-it-AWQ-4bitgemma-4-E4B-it-MLX-4bitLlama-3.1-8B-Instruct-4bite5-mistral-7b-instruct-bnb-4bitQwen3-Coder-30B-A3B-Instruct-AWQ-4bitQwen3-VL-8B-Instruct-AWQ-4bitQwen3.5-4B-AWQ-4bitQwen3.5-9B-MLX-4bitgemma-4-26B-A4B-it-QAT-MLX-4bitgemma-3-12b-it-4bitmistral-7b-v0.3-bnb-4bitQwen3.6-35B-A3B-AWQ-4bitgemma-4-E4B-it-unsloth-bnb-4bitQwen3.6-27B-MLX-4bitgemma-4-12B-it-MLX-4bitQwen2.5-14B-bnb-4bitDeepSeek-R1-0528-Qwen3-8B-MLX-4bitQwen3.6-35B-A3B-MLX-4bitOrnith-1.5-9B-MLX-4bitQwen3.8-27B-unsloth-bnb-4bitQwen3-VL-4B-Instruct-unsloth-bnb-4bitQwen2.5-Coder-7B-Instruct-4bitgemma-4-31B-it-AWQ-4bitgemma-4-E2B-it-MLX-4bitOrnith-1.5-35B-A3B-MLX-4bitQwen3.6-27B-GPTQ-Pro-4bitQwen3-30B-A3B-Instruct-2507-AWQ-4bitQwen3.5-27B-AWQ-4bitQwen3-14B-unsloth-bnb-4bit
