bpx03 /
QEngine
Source-available C++/CUDA inference engine for Qwen3.8-27B INT4 on 3x RTX 3090
Updated 20 min ago
Why now
Version v1.3.1 came out on October 30.
+26 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
The README covers a Docker image, a Python server with OpenAI and Anthropic compatible APIs, and an image-input Flash-Next variant that runs on 2 or 3 RTX 3090s. It does not state an install procedure outside Docker.
Summary written by AI from the repository’s description and README.
bpx03 / QEngine
View on GitHub(opens in new tab)