Soul-AILab/
SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.
by Soul AI Lab Python Apache-2.0 licence 148 forks Created Dec 2025 View on GitHub
- Stars
- 1,564
- 16% of Soul-AILab's stars
- Rank
- #43,892
- of 851,979 repos, top 6%
- In Python
- #7,878
- of 173,293 repos, top 5%
Among 851,979 repos
1k–1.6k stars: 23,673 repos, including SoulX-FlashTalk
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 #43,865
- Next milestone
- +5,651 stars to reach the top 1%
- Popular
- One of 66,555 repos with 1k+ stars