tokenspeed
TokenSpeed is a speed-of-light LLM inference engine.
lightseekorg/tokenspeed
View on GitHub ↗TokenSpeed is a speed-of-light LLM inference engine.
tokenspeed grew +28.0% in the last 30 days, ranks 66th of 496 in Local Runtime / Inference Engine, actively maintained, last commit today.
Star trajectory
80 days tracked2026-08-072.8k stars today2026-10-26
Momentum
+28.0% in 30d, above the Local Runtime / Inference Engine median of +1.7%.
Maintenance
Last commit today, fresher than the median of 6d.
How it compares in Local Runtime / Inference Engine
tokenspeed
2.8k
stars
+28.0% 30d
commit today
Local Runtime / Inference Engine median
409.5
stars
+1.7% 30d
commit ~6d ago
Leader · ollama
184.8k
stars
+1.7% 30d
commit today
Ranked 66th of 496 by stars.
turboderp/exllama2.9k-160deeplethe/forkd2.9k-115
lightseekorg/tokenspeed2.8k
FasterDecoding/Medusa2.8k+10janhq/nitro2.7k+37- Language
- Python
- License
- MIT License
- Contributors
- 103
- Forks
- 377
- Watchers
- 18
- Open issues
- 9
- Releases
- 2
- Created
- 2026-05-06
- Stars this week
- +76
You've seen where tokenspeed stands today.
Get the moves before everyone else: the 5 Local Runtime / Inference Engine repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.