The Local LLM Index / Quantization & Formats / #69
ddalcu/mlx-serve
by ddalcu · Quantization & Formats · updated today
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
67
momentum
1,239
stars
114
forks
#69
rank
agentanthropic-apiapple-siliconclaude-codedeepseek-v4diffusionggufimage-generationinferencellmlocal-llmmacos
View on GitHub →