vllm-mlx

vLLM-like inference for Apple Silicon - GPU-accelerated Text, Image, Video & Audio on Mac

vllm-mlx has been downloaded 52,145 times in total on PyPI, including 6,640 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
52.15k
LicenseApache-2.0
Authorvllm-mlx contributors
UpdatedMay 21, 2026

Downloads

Weekly, last 90d.
Includes CI traffic.

VersionsTotal0.*
Range
View
Granularity
Group by
CI traffic
Stack: OffCI: Included2 / 12 series
Selected total54.74k
52.1kAll-time
6.6kLast 30 days
190Last 24 h
<0.01/sPer second

Version distribution

Share of downloads by released version. Computed over the last quarter.

  • 01

    0.3.0

    10.4k downloads
    38.5%
  • 02

    0.2.5

    6.9k downloads
    25.5%
  • 03

    0.4.0

    5.8k downloads
    21.6%
  • 04

    0.4.0rc1

    957 downloads
    3.6%
  • 05

    0.2.6

    637 downloads
    2.4%
  • 06

    0.2.9

    500 downloads
    1.9%
  • 07

    0.2.8

    451 downloads
    1.7%
  • 08

    0.2.1

    425 downloads
    1.6%
  • 09

    Other

    923 downloads
    3.4%

Guess the next day

Thirteen recent days of vllm-mlx downloads. Drag the green handle on the right to guess where day fourteen lands.

TRUTH190439WEDTHUFRISATSUNMONTUEWEDTHUFRISATSUNMON