vllm-mlx

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

vllm-mlx has been downloaded 69,462 times in total on PyPI, including 18,687 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
69.46k
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 / 13 series
Selected total70.11k
69.5kAll-time
18.7kLast 30 days
121Last 24 h
<0.01/sPer second

Version distribution

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

  • 01

    0.4.1

    15.3k downloads
    43.7%
  • 02

    0.2.5

    6.6k downloads
    18.8%
  • 03

    0.4.0

    6.1k downloads
    17.3%
  • 04

    0.3.0

    4.4k downloads
    12.7%
  • 05

    0.2.6

    492 downloads
    1.4%
  • 06

    0.4.0rc1

    463 downloads
    1.3%
  • 07

    0.2.9

    354 downloads
    1.0%
  • 08

    0.2.8

    335 downloads
    1.0%
  • 09

    Other

    995 downloads
    2.8%

Guess the next day

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

TRUTH12150SATSUNMONTUEWEDTHUFRISATSUNMONTUEWEDTHU
    vllm-mlx · 69.5k downloads on PyPI