Incusvsllama.cpp
Two self-hosted projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.
| Incus | llama.cpp | |
|---|---|---|
| Score | 75/100 | 93/100 |
| Rank in category | #3 of 44 in Container Management | #2 of 25 in LLM Inference |
| GitHub stars | 6 516 | 132 663 |
| Stars, last 30 days | +276 | +3 306 |
| Stable releases, 12 months | 16 | 1460 |
| Latest release | v7.0.2 · 16 Oct 2026 | b11971 · 28 Oct 2026 |
| Setup | Advanced | Moderate |
| Official Docker image | Yes | Yes |
| License | Apache-2.0 | MIT |
| Main language | Go | C++ |
Which one should you pick?
llama.cpp scores 93/100 against 75/100 for Incus, so it is the safer default.
llama.cpp ships more often: 1460 stable releases in the past year, against 16 for Incus.
If you want the quickest setup, llama.cpp is easier to run; Incus needs more configuration.
llama.cpp is growing faster right now (+3 306 stars in 30 days).
Incus details →llama.cpp details →
Swap a project
Keep Incus, compare it with
Keep llama.cpp, compare it with