vllm-mlx
vLLM-like inference for Apple Silicon - GPU-accelerated Text, Image, Video & Audio on Mac
vllm-mlx has been downloaded 75,928 times in total on PyPI, including 7,197 in the last 30 days. The latest version is 0.4.0rc1, released May 21, 2026. It is distributed under the Apache-2.0 license.
Version0.4.0rc1
Downloads
75.93k
LicenseApache-2.0
Authorvllm-mlx contributors
Downloads
Weekly, last 90d.
Includes CI traffic.
VersionsTotal0.*
Range
View
Granularity
Group by
CI traffic
Stack: OffCI: Included2 / 14 series
Selected total70.74k
75.9kAll-time
7.2kLast 30 days
1.3kLast 24 h
<0.01/sPer second
Sponsored
Sponsorships keep pepy free to read
Version distribution
Share of downloads by released version. Computed over the last quarter.
- 0148.9%
0.4.1
17.2k downloadsDownloads17.2k48.9% - 0217.5%
0.4.0
6.2k downloadsDownloads6.2k17.5% - 0313.0%
0.2.5
4.6k downloadsDownloads4.6k13.0% - 0412.2%
0.5.0
4.3k downloadsDownloads4.3k12.2% - 053.0%
0.3.0
1.0k downloadsDownloads1.0k3.0% - 061.0%
0.2.6
366 downloadsDownloads3661.0% - 070.8%
0.2.9
278 downloadsDownloads2780.8% - 080.8%
0.2.8
267 downloadsDownloads2670.8% - 092.9%
Other
1.0k downloadsDownloads1.0k2.9%
Guess the next day
Thirteen recent days of vllm-mlx downloads. Drag the green handle on the right to guess where day fourteen lands.