jesdga95 /
basalt
Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell
Updated 1 h ago
Maintain this repo? Add this badge to your README.
Why now
Version v0.2.0 came out on November 1.
+209 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
It needs Linux or Windows on an NVIDIA Blackwell GPU with CUDA 13, plus enough system RAM for offloaded experts. It serves an OpenAI- and Anthropic-compatible API on localhost.
Summary written by AI from the repository’s description and README.
jesdga95 / basalt
View on GitHub(opens in new tab)