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 →

7.0

GitHub Metrics

Stars

1.6k

Forks

219

Open Issues

Watchers

Contributors

Weekly Commits

Language

Python

License

Apache-2.0

Last Commit

Aug 26, 2026

Created

Dec 6, 2025

Latest Release

v0.4.1

Release Date

Aug 12, 2026

Synced: Aug 28, 2026

Quality Scores

Documentation Qualityw: 20%

7.1

Has docs site (https://pypi.org/project/vllm-mlx/). Description: 183 chars. Stars signal: 1,550. Contributors: 57. Score: 7.1/10

Community Healthw: 20%

5.8

Stars: 1,550. Contributors: 57. Watchers: 12. Forks: 218. Issue ratio: 5.0%. Score: 5.8/10

Maintenance Velocityw: 15%

9.1

Last commit: 1d ago. Weekly commits: 5. Latest release: v0.4.1. Score: 9.1/10

API Design & DXw: 20%

6.7

Stars/issues ratio: 20. Dynamic language: Python. Has documentation site. Permissive license: Apache-2.0. Popularity signal: 1,550 stars. Score: 6.7/10

Production Readinessw: 15%

6.6

Battle-tested: 1,550 stars. Peer review: 57 contributors. Versioned: v0.4.1. Licensed: Apache-2.0. Age: 0.7 years. Maintenance: last commit 1d ago. Score: 6.6/10

Ecosystem Integrationw: 10%

7.3

Fork interest: 218. Major ecosystem: Python. Integration-friendly: Apache-2.0. Adoption: 1,550 stars. Has web presence. Score: 7.3/10