lrozewicz/vLLM-Moet-GB10

Run DeepSeek-V4-Flash 304B on a single NVIDIA GB10 / DGX Spark - 2-bit MoE planes, FP4 quality recovery, speculative decoding

13
Stars
3
Forks
30.6
Radar Score
Rising
Momentum

Scoring Breakdown

Impact4.4
Velocity44.1
Health53.7

Growth Metrics

7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Sass

Why it ranks

Steady growth — consistently collecting stars and contributors.

LLM FrameworksTop 81% globally
View on GitHub