llama.cppvsmarm-memory
Two self-hosted projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.
| llama.cpp | marm-memory | |
|---|---|---|
| Score | 93/100 | 53/100 |
| Rank in category | #2 of 25 in LLM Inference | #26 of 120 in AI Assistant |
| GitHub stars | 132 674 | 424 |
| Stars, last 30 days | +3 317 | — |
| Stable releases, 12 months | 1461 | 10 |
| Latest release | b11972 · 28 Oct 2026 | v2.60.1 · 12 Oct 2026 |
| Setup | Moderate | Moderate |
| Official Docker image | Yes | Yes |
| License | MIT | Apache-2.0 |
| Main language | C++ | Python |
Which one should you pick?
llama.cpp scores 93/100 against 53/100 for marm-memory, so it is the safer default.
llama.cpp ships more often: 1461 stable releases in the past year, against 10 for marm-memory.
llama.cpp is growing faster right now (+3 317 stars in 30 days).
llama.cpp details →marm-memory details →