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.
Llama-3.1-8B-Instruct-4bitLFM2.5-1.2B-Instruct-MLX-8bitLFM2.5-1.2B-Instruct-MLX-4bitLFM2.5-1.2B-Instruct-MLX-6bitLFM2-24B-A2B-MLX-4bitLFM2-24B-A2B-MLX-5bitLFM2-24B-A2B-MLX-8bitLFM2-24B-A2B-MLX-6bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5bitLlama-3.2-1B-Instruct-4bitLFM2-1.2B-MLX-8bitLFM2-1.2B-MLX-bf16Llama-3.2-3B-Instruct-4bitDevstral-Small-2505-MLX-4bitMeta-Llama-3.1-8B-Instruct-4bitgranite-4.2-8b-MLX-8bitLlama-3.3-70B-Instruct-4bitLFM2.5-1.2B-Instruct-4bitLFM2.5-2.6B-MLX-8bitNVIDIA-Nemotron-3.5-Lightning-30B-A3B-4bitLFM2.5-8B-A1B-MLX-4bitLlama-3.3-70B-Instruct-8bitMeta-Llama-3.1-8B-Instruct-8bitLlama-3.2-3B-Instruct-8bitSmolLM3-3B-4bitLFM2.5-2.6B-4bitLlama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-8Bit