experts4bit-qlora
Train and serve Mixture-of-Experts models that do not fit in VRAM: fused 4-bit experts, QLoRA, CPU/NVMe offload, and fast inference on consumer NVIDIA GPUs.
v0.37.4MIT
AI Health Summary — Claude-generated analysis of download trends, maintenance, and risk signals.
Upgrade to PRONo known vulnerabilities in the latest version
Based on latest version 0.37.4. If you're running an older version, check OSV for your specific version.
Exclude CI/CDPRO
Best Day
651
Sep 3
Worst Day
3
Sep 17
Peaks On
Thus
222 avg
Quietest
Suns
61 avg
Download Trend
Badge
Markdown
[](/packages/experts4bit-qlora)
HTML
<a href="/packages/experts4bit-qlora"><img src="/api/badges/experts4bit-qlora?period=month" alt="PyPI Stats"></a>