llama.cpp
LLM inference in C/C++
llama.cpp scores 8.6/10 (Strong) in Inference & Serving.
Language C++ License MIT Stars 119k★ Type lightweight Self-host Yes Repo ggml-org/llama.cpp Homepage https://github.com/ggml-org/llama.cpp
Quality
Strong 8.6
Adoption 77
Activity 97
Maturity 97
Community 83
Capability 50
Show the math
Overall 8.6/10
value = 8.6/10
score = value
Adoption 7.9/10
value = 76.9/100
score = 1 + 9 * value / 100
Activity 9.7/10
value = 96.9/100
score = 1 + 9 * value / 100
Maturity 9.8/10
value = 97.4/100
score = 1 + 9 * value / 100
Community 8.5/10
value = 83/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
119.2k★ GitHub stars
1.2k/90d Recent commits
49 devs/90d Recent contributors
3.3y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
cpu gguf quantization ggml server