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.
MiniCPM-SALA-AWQ-8bitOrnith-1.5-9B-MLX-8bitDeepSeek-R1-0528-Qwen3-8B-MLX-8bitGLM-4.7-Flash-MLX-8bitOrnith-1.5-35B-A3B-MLX-8bitQwen3-Coder-30B-A3B-Instruct-MLX-8bitLFM2-24B-A2B-MLX-8bitLFM2.5-1.2B-Instruct-MLX-8bitQwen2.5-Coder-14B-Instruct-MLX-8bitQwen3-0.6B-8bitQwen3-14B-MLX-8bitQwen3-8B-MLX-8bitQwen2.5-Coder-32B-Instruct-MLX-8bitQwen3-32B-MLX-8bitQwen3-4B-Instruct-2507-MLX-8bitQwen3-4B-Thinking-2507-MLX-8bitNVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8bitgpt-oss-120b-MLX-8bitQwen3-1.7B-MLX-8bitSeed-OSS-36B-Instruct-MLX-8bitQwQ-32B-MLX-8bitQwen3-30B-A3B-Instruct-2507-MLX-8bitQwen3-4B-MLX-8bitERNIE-4.5-21B-A3B-MLX-8bitLFM2-1.2B-MLX-8bitMiniMax-M2.5-MLX-8bitOrnith-1.0-9B-MLX-8bitQwen3.8-Flash-Next-MLX-Serve-mixed-4-8bitQwen3-Next-80B-A3B-Instruct-MLX-8bitQwen3-30B-A3B-MLX-8bit
