llama.cppvsTiramisu
Two self-hosted projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.
| llama.cpp | Tiramisu | |
|---|---|---|
| Score | 93/100 | 47/100 |
| Rank in category | #2 of 25 in LLM Inference | #40 of 54 in Media Streaming |
| GitHub stars | 132 699 | 149 |
| Stars, last 30 days | +3 244 | +0 |
| Stable releases, 12 months | 1464 | 10 |
| Latest release | b11978 · 29 Oct 2026 | v1.11.8 · 17 Oct 2026 |
| Setup | Moderate | Advanced |
| Official Docker image | Yes | Yes |
| License | MIT | Other |
| Main language | C++ | Go |
Which one should you pick?
llama.cpp scores 93/100 against 47/100 for Tiramisu, so it is the safer default.
llama.cpp ships more often: 1464 stable releases in the past year, against 10 for Tiramisu.
If you want the quickest setup, llama.cpp is easier to run; Tiramisu needs more configuration.
llama.cpp is growing faster right now (+3 244 stars in 30 days).
llama.cpp details →Tiramisu details →