raullenchai / Rapid-MLX
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.
Why this job: says: inference server, llm inference; topics: apple-silicon, local-llm, llm-inference, local-ai, mlx
What it does
Measured speed on a Mac Studio M5 Max (36 GB) — Rapid-MLX 0.16.1 vs oMLX 0.7.0 and LM Studio, using the same base 4-bit weights for each model.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 4,122
- +32 this week
- Licence
- Custom
- Read before business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.0.2
- Released 4 days ago
- Built with
- Python
- 79% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 100% closed
- 3 still open
- Pull requests
- 3,157 merged
- 4 waiting
- Releases
- 282
- 30+ in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| waybarrios / vllm-mlx | 1,651 | 3 days ago | Apache-2.0 | No downloads |
| jundot / omlx | 23,491 | 5 days ago | Apache-2.0 | Mac |
| incoai / splash | 2,170 | 4 days ago | Apache-2.0 | Mac |
More: languages, topics, project record and preview image
Languages
- Python 79%
- Swift 19%
- Shell 2%
- HTML <1%
Topics
- apple-silicon
- local-llm
- macos
- mlx
- tool-calling
- ollama-alternative
- claude-code
- anthropic-api
- coding-agents
- continuous-batching
- inference-server
- llm-inference
Project record
- JobLocal LLMs
- StatusListed
- Commits3,694
- Forks440
- Watching64
- Stars in 28 days+159
- CreatedFeb 25, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026