antirez /
ds4
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Updated 41 min ago
+118 stars gained this week
Stars gained each day, last 30 days
Usual pace · 51 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
A small, self-contained native inference engine for running a few specific large language models, such as DeepSeek V4 Flash, on Metal, CUDA and ROCm hardware. It targets people running models on consumer machines.
Summary written by AI from the repository’s description and README.
antirez / ds4
View on GitHub(opens in new tab)