Infatoshi/
Qwen3-0.6B megakernel: 527 tok/s decode on RTX 3090 (3.8x faster than PyTorch)
by Elliot Arledge Cuda 11 forks Created Jan 2026 View on GitHub
- Stars
- 145
- 2% of Infatoshi's stars
- Rank
- #361,609
- of 852,369 repos, top 43%
Among 852,369 repos
100–160 stars: 155,646 repos, including MegaQwen
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #359,679
- Next milestone
- +11 stars to reach the top 40%
- Popular
- One of 490,939 repos with 100+ stars