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.
LFM2-24B-A2B-MLX-5bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5bitNVIDIA-Nemotron-3-Super-120B-A12B-5bitLFM2.5-2.6B-MLX-5bitgranite-4.2-8b-5bit-mlxLFM2.5-8B-A1B-MLX-5bitLFM2.5-1.2B-Thinking-MLX-5bitLFM2.5-2.6B-MLX-5bitgranite-4.2-3b-5bit-mlxLFM2.5-1.2B-Instruct-MLX-5bitgranite-4.2-30b-5bit-mlxLFM2.5-350M-MLX-5bitLFM2.5-230M-MLX-5bitDolphin-X1-Trinity-Nano-5bit-MLXNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5BitLFM2.5-1.2B-Instruct-5bitLFM2.5-2.6B-5bitEuroLLM-22B-Instruct-2512-mlx-5bitLlama-3.2-3B-Instruct-Q5_K_M-GGUFMinistral-3-14B-Instruct-2512-heretic-mlx-5bitLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-5BitQwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-mlx-5BitMistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-5BitTrinity-Nano-Preview-MLX-5bitgranite-4.2-3b-5bit-awq-mlxgranite-4.2-8b-5bit-awq-mlxDevstral-Small-2507-5bitK-EXAONE-236B-A23B-5bitLFM2.5-1.2B-Thinking-5bitLlama3.3-8B-Instruct-Thinking-Claude-4.5-Opus-High-Reasoning-mlx-5Bit