PyRank
waybarrios

vllm-mlx

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.
PyPI GitHub
More links
Download Stats Issues Release Notes
Verified repo
Monthly downloads
6.0K
Weekly downloads
527
GitHub stars
1.6K

Downloads in the 30 and 7 days to October 10, 2026. Refreshed weekly.

Package Information

Latest Version
0.5.0
Requires Python
>=3.10
Licence
Apache-2.0
Last Release
4 weeks ago
Author
vllm-mlx contributors
First Release
January 6, 2026
Total Releases
13
Python Versions
3 3.10 3.11 3.12 3.13
No reported malware or high/critical advisories · Details

The current version has no OSV.dev malware reports and no critical or high-severity vulnerabilities.

Package Insights

What's this?
Score breakdown - each component scores 0-100, weighted by percentage
Maintenance
90
Popularity
68
Adoption
37
Community
70
Provenance
100
How the maintenance status was determined
Last commit
6 days ago
Monthly downloads
6,010
• Active
Activity within 30 days
Stable
Activity within 31-180 days
Minimal
Activity within 181-365 days, or no activity data
At Risk
No activity for > 365 days, but > 10,000 monthly downloads
Archived
Repository flagged as archived on GitHub
How the popularity category was determined
Monthly downloads
6,010
Stars
1,618
Stars per 1k downloads
269.22
Industry Standard
> 10,000,000 monthly downloads
Hidden Gem
< 0.5 stars per 1k downloads and > 100,000 monthly downloads
• Community Favorite
> 5 stars per 1k downloads
Rising Star
Balanced ratio of stars to downloads
Unknown
Fewer than 1,000 monthly downloads, or no star data
How download momentum is calculated
Week daily avg
75
Month daily avg
200
Momentum
-62.4%
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100
More insights and metrics
Python version support tiers
requires_python
>=3.10
Cutting Edge
Minimum supported version is 3.14 or newer
Modern
Minimum supported version is 3.11 to 3.13
• Legacy
Supports 3.10 or older (or Python 2)
Unknown
No requires_python specified or unparseable
License categories
License
Apache-2.0
• Permissive
MIT, Apache, BSD, ISC, Unlicense, CC0, etc.
Copyleft
GPL, LGPL, AGPL, MPL, EPL, etc.
Proprietary
Commercial, all rights reserved, custom EULAs
Unknown
No license specified, or none of the above match
How the release cadence was determined
Last release
28 days ago
Total releases
13
Releases/year
16.8
• Rapid
Last release within 365 days and > 12 releases/year
Regular
Last release within 365 days
Slow
Last release 366-730 days ago
Stalled
Last release > 730 days ago, or no releases
Unknown
No usable release date available
How contributor risk was determined
Contributors
60
Monthly downloads
6,010
High Load
≤ 2 contributors and ≥ 50,000 monthly downloads
Moderate Load
< 10 contributors and ≥ 500,000 monthly downloads
Low Load
< 25 contributors and ≥ 5,000,000 monthly downloads, or sole maintainer with ≥ 10,000 monthly downloads
• Balanced
Enough contributors for the package's popularity
Unknown
No contributor data available
Engagement
77
 
Issue Burden
45.1
per 1k stars
Discussions
9.9
per 1k stars
Fork Ratio
26.0%
contrib / forks
Stale Release
No
 
PR Velocity
Active
 
Not all downloads include detailed metadata. Breakdowns reflect the subset that does.

Downloads by OS

macOS 28
Linux 7

Python Versions

3.12
71.4% 25
3.14
14.3% 5
3.11
5.7% 2
3.13
5.7% 2
3.10
2.9% 1

Top Countries

1. US US
33
2. GB GB
5
3. JP JP
4
4. FR FR
3
5. SG SG
3
6. CA CA
2
7. DE DE
2
8. TW TW
2
9. AU AU
1
10. BD BD
1

Weekly Downloads

GitHub Stars

Dependencies

26
26 optional dependencies
  • anyio>=4.0[dev]
    extra == "dev"
  • black>=23.0.0[dev]
    extra == "dev"
  • cn2an>=0.5.0[audio]
    extra == "audio"
  • fugashi>=1.3.0[audio]
    extra == "audio"
  • jieba>=0.42.0[audio]
    extra == "audio"
  • loguru>=0.7.0[audio]
    extra == "audio"
  • misaki>=0.5.0[audio]
    extra == "audio"
  • mlx-audio>=0.2.9[audio]
    extra == "audio"
  • mypy>=1.0.0[dev]
    extra == "dev"
  • num2words>=0.5.0[audio]
    extra == "audio"
  • numba>=0.57.0[audio]
    extra == "audio"
  • openai-harmony>=0.0.8[harmony]
    extra == "harmony"
  • ordered-set>=4.1.0[audio]
    extra == "audio"
  • phonemizer>=3.2.0[audio]
    extra == "audio"
  • pre-commit>=4.6.0[dev]
    extra == "dev"
  • pytest>=7.0.0[dev]
    extra == "dev"
  • ruff>=0.1.0[dev]
    extra == "dev"
  • scipy>=1.10.0[audio]
    extra == "audio"
  • sounddevice>=0.4.0[audio]
    extra == "audio"
  • soundfile>=0.12.0[audio]
    extra == "audio"
  • spacy>=3.7.0[audio]
    extra == "audio"
  • tiktoken>=0.5.0[audio]
    extra == "audio"
  • torch>=2.8.0[vision]
    extra == "vision"
  • torchvision>=0.23.0[vision]
    extra == "vision"
  • unidic-lite>=1.0.0[audio]
    extra == "audio"
  • vllm>=0.4.0[vllm]
    extra == "vllm"

Used By

1

Data and sources

Tracking Since
September 26, 2026
Data Updated
October 11, 2026
Data Freshness
Fresh
Keywords
llm mlx apple-silicon vllm inference-server openai-api anthropic-api continuous-batching multimodal local-llm
Sources and methodology