Rapid-MLX
by raullenchaiIn its repository's words: “Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.”
Facts from GitHub
- Licence
- Apache-2.0 (Apache License 2.0), permissive, our reading
- Activity
- Last push 19 Nov 2026: pushed to in the last 90 days
- Latest release
- not fetched yet
- Stars
- 4.2k
- Main language
- Python
- On GitHub since
- 25 Feb 2026
- Topics
- anthropic-api, apple-silicon, claude-code, coding-agents, continuous-batching, inference-server, llm-inference, llm-server, lm-studio-alternative, local-ai, local-llm, macos, mcp, mlx, mlx-lm, ollama-alternative, omlx-alternative, openai-compatible, speculative-decoding, tool-calling
What it says it supports
- Loads
- MLX
- Runs on
- macOS
- Hardware
- Apple silicon
Each item is on our list for this tool and named in its README. A mention is not a test: check the project's documentation for your setup.
Reviewed models it can load
Matched by file format only, from our snapshot of the Hub: GGUF where we measured GGUF files, other formats where a conversion exists, safetensors for the original weights. Support for a new architecture can lag behind its release.
MLX 284
openai-community/gpt2, Qwen/Qwen3-0.6B, Qwen/Qwen3-14B, deepseek-ai/DeepSeek-V3.2, Qwen/Qwen3.8-27B, Qwen/Qwen3.5-9B, Qwen/Qwen2.5-7B-Instruct, zai-org/GLM-5.3-Flash, Qwen/Qwen3-VL-8B-Instruct, google/gemma-4-31B-it, Qwen/Qwen3-8B, baidu/Unlimited-OCR, and 272 more, most downloaded first
Other tools in Run locally
Tool data from the GitHub API, fetched 19 Nov 2026, 15:36 UTC. Listing is not endorsement and nobody can pay to be listed. Something wrong here? Write to hello@weightsnotwalls.com.