ggrun
llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.
raketenkater/ggrun
View on GitHub ↗llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.
ggrun grew +1.8% in the last 30 days, ranks 293rd of 494 in Local Runtime / Inference Engine, actively maintained, last commit yesterday.
Star trajectory
115 days tracked2026-07-02282 stars today2026-10-25
Momentum
+1.8% in 30d, above the Local Runtime / Inference Engine median of +1.7%.
Maintenance
Last commit yesterday, fresher than the median of 5d.
How it compares in Local Runtime / Inference Engine
ggrun
282
stars
+1.8% 30d
commit yesterday
Local Runtime / Inference Engine median
414
stars
+1.7% 30d
commit ~5d ago
Leader · ollama
184.7k
stars
+1.7% 30d
commit today
Ranked 293rd of 494 by stars.
armbues/SiLLM282+0portofcontext/pctx282+0
raketenkater/ggrun282
JosefAlbers/phi279+3codecoradev/uteke276+6- Language
- Go
- License
- MIT License
- Contributors
- 3
- Forks
- 19
- Watchers
- 3
- Open issues
- 1
- Releases
- 10
- Created
- 2026-03-11
- Stars this week
- +2
You've seen where ggrun 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.