gptqmodel
Production ready LLM model compression/quantization toolkit with hw accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang.
gptqmodel has been downloaded 470,185 times in total on PyPI, including 35,128 in the last 30 days. The latest version is 7.5.0, released Sep 15, 2026.
Version7.5.0
Downloads
470.19k
License—
AuthorModelCloud
UpdatedSep 15, 2026
Downloads
Weekly, last 90d.
Includes CI traffic.
VersionsTotal7.*6.*
Range
View
Granularity
Group by
CI traffic
Stack: OffCI: Included3 / 64 series
Selected total155.10k
470.2kAll-time
35.1kLast 30 days
1.0kLast 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.
- 0111.4%
7.3.2
11.1k downloadsDownloads11.1k11.4% - 027.3%
7.1.0
7.2k downloadsDownloads7.2k7.3% - 037.3%
7.5.0
7.1k downloadsDownloads7.1k7.3% - 044.3%
7.3.1
4.2k downloadsDownloads4.2k4.3% - 054.3%
7.3.5
4.2k downloadsDownloads4.2k4.3% - 064.3%
7.3.6
4.2k downloadsDownloads4.2k4.3% - 074.2%
5.8.0
4.1k downloadsDownloads4.1k4.2% - 084.1%
7.0.0
4.0k downloadsDownloads4.0k4.1% - 0952.8%
Other
51.6k downloadsDownloads51.6k52.8%
Guess the next day
Thirteen recent days of gptqmodel downloads. Drag the green handle on the right to guess where day fourteen lands.