exllama
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
turboderp/exllama
View on GitHub ↗A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
exllama grew -0.0% in the last 30 days, ranks 64th of 494 in Local Runtime / Inference Engine, last commit 1,120 days ago.
Star trajectory
122 days tracked2026-06-252.9k stars today2026-10-25
Momentum
-0.0% in 30d, below the Local Runtime / Inference Engine median of +1.7%.
Maintenance
Last commit 1,120 days ago, staler than the median of 5d.
How it compares in Local Runtime / Inference Engine
exllama
2.9k
stars
-0.0% 30d
commit 1,120 days ago
Local Runtime / Inference Engine median
414
stars
+1.7% 30d
commit ~5d ago
Leader · ollama
184.7k
stars
+1.7% 30d
commit today
Ranked 64th of 494 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 16
- Forks
- 219
- Watchers
- 34
- Open issues
- 61
- Releases
- 0
- Created
- 2023-05-04
- Stars this week
- +2
You've seen where exllama 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.