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.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest 1 day ago, with 48 contributors on GitHub.
Gained 72% fewer stars in the last 90 days than in the 90 days before.
Use Cases & Benefits
- Runs local AI models on Apple Silicon Macs as a drop-in OpenAI API replacement with fast inference and full tool calling support.
- Delivers up to 4.2x faster performance than alternatives like Ollama by leveraging Apple's MLX framework and optimized caching techniques.
- Use for deploying private, cost-effective AI servers on Mac hardware without cloud dependency or API fees.
- Use for integrating advanced tool calling and reasoning capabilities into coding assistants and chatbots compatible with OpenAI API clients.
- Use for benchmarking and running large-scale language models optimized for Apple Silicon with support for multiple model sizes and formats.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Other
GitHub could not identify this license; read the LICENSE file before depending on it.
Community files
- README: present
- Contributing guide: present
Watch-outs
- License not identified by GitHub; read the LICENSE file before depending on it.
General guidance from repository metadata, not legal advice. How we score
From the README
Run AI on your Mac. Faster than anything else.
Run local AI models on your Mac — no cloud, no API costs. Works with Cursor, Claude Code, and any OpenAI-compatible app.
pip install → serve Gemma 4 26B → chat + tool calling → works with PydanticAI, LangChain, Aider, and more.
"No matching distribution" error? Your Python is too old. Run
python3 --version— if it says 3.9, install a newer Python:brew install [email protected]thenpython3.12 -m pip install rapid-mlxFirst run downloads the model (~14 GB) — you'll see a progress bar. Wait for
Ready: http://localhost:8000/v1.Step 3 — Chat (open a second terminal tab):
That's it — you now have an OpenAI-compatible AI server on
localhost:8000. Point any app athttp://localhost:8000/v1and it just works.Tip: Run
rapid-mlx modelsto see all available model aliases. For a smaller/faster model, tryrapid-mlx serve qwen3.5-9b(~5 GB).
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+602 stars over 79 days across 7 snapshot days; best day +8 on Oct 7.
Forks
438+38
Open issues
14-16
Compared with peers in Backend
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| anthropics/skills | 187.8K | +2.9K | 15 | — |
| DuarteSantos8/openGym | 19.7K | +2.4K | 60 | 2 days ago |
| shiyu-coder/Kronos | 47.0K | +2.3K | 16 | — |
| NationalSecurityAgency/ghidra | 98.2K | +2.3K | 64 | 14 days ago |
| microsoft/VibeVoice | 56.0K | +1.1K | 29 | — |
| raullenchai/Rapid-MLX | 4.1K | — | 60 | 1 day ago |
| Category median | 56.0K | +2.3K | 29 | — |
Discover Repositories
Search across tracked repositories by name or description