Blazing fast Apple Silicon optimized inference engine built for Qwen and Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
Like nace-ai/kapitsa, 0 likes 0 Bookmark nace-ai/kapitsa, 0 bookmarks 0 Fastest LLM inference runtime for Apple Silicon
Like basecompute/baseRT, 0 likes 0 Bookmark basecompute/baseRT, 0 bookmarks 0 🔥 The fastest local AI engine for Apple Silicon. Optimised for agentic use.
Like samuelfaj/lightning-mlx, 0 likes 0 Bookmark samuelfaj/lightning-mlx, 0 bookmarks 0 A local inference engine for Apple silicon, built around the model.
Like incoai/splash, 0 likes 0 Bookmark incoai/splash, 0 bookmarks 0 lithos-metal: high-performance LLM inference kernels and serving for Apple silicon.
Like lithos-ai/lithos-metal, 0 likes 0 Bookmark lithos-ai/lithos-metal, 0 bookmarks 0 Metal-first MoE inference for Apple Silicon with bounded SSD expert streaming and local OpenAI Chat, Responses, and Anthropic Messages endpoints.
Like hebrus-labs/hebrus, 0 likes 0 Bookmark hebrus-labs/hebrus, 0 bookmarks 0 Big models. Small Macs. Zero excuses.
Like zouyee/dmlx, 0 likes 0 Bookmark zouyee/dmlx, 0 bookmarks 0 High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
Like waybarrios/vllm-mlx, 0 likes 0 Bookmark waybarrios/vllm-mlx, 0 bookmarks 0 macMLX brings local LLM inference to Apple Silicon with a first-class native macOS experience. No cloud, no telemetry, no Electron — just your Mac running models at full speed.
Like magicnight/Mac-MLX, 0 likes 0 Bookmark magicnight/Mac-MLX, 0 bookmarks 0 
