waybarrios/vllm-mlx

Model Serving

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.

GitHub →Website →

6.9

GitHub Metrics

Stars

1.6k

Forks

241

Open Issues

104

Watchers

Contributors

Weekly Commits

Language

Python

License

Apache-2.0

Last Commit

Oct 17, 2026

Created

Dec 6, 2025

Latest Release

v0.5.0

Release Date

Sep 17, 2026

Synced: Oct 18, 2026

Quality Scores

Documentation Qualityw: 20%

7.1

Has docs site (https://pypi.org/project/vllm-mlx/). Description: 183 chars. Stars signal: 1,625. Contributors: 65. Score: 7.1/10

Community Healthw: 20%

5.5

Stars: 1,625. Contributors: 65. Watchers: 10. Forks: 239. Issue ratio: 6.4%. Score: 5.5/10

Maintenance Velocityw: 15%

8.6

Last commit: 1d ago. Weekly commits: 3. Latest release: v0.5.0. Score: 8.6/10

API Design & DXw: 20%

6.7

Stars/issues ratio: 16. Dynamic language: Python. Has documentation site. Permissive license: Apache-2.0. Popularity signal: 1,625 stars. Score: 6.7/10

Production Readinessw: 15%

6.7

Battle-tested: 1,625 stars. Peer review: 65 contributors. Versioned: v0.5.0. Licensed: Apache-2.0. Age: 0.9 years. Maintenance: last commit 1d ago. Score: 6.7/10

Ecosystem Integrationw: 10%

7.4

Fork interest: 239. Major ecosystem: Python. Integration-friendly: Apache-2.0. Adoption: 1,625 stars. Has web presence. Score: 7.4/10