ggml-org/llama.cpp has 866,571 source lines of code out of 1,110,197 total lines across 3,414 files, counted with tokei from the master ref at commit 8bfd64b5ac86 on November 16, 2026. Tests, docs and generated files are excluded under OctoCounts' canonical public options.
As of 2026-11-16 (commit 8bfd64b5ac86), ggml-org/llama.cpp contains 1,110,197 total lines: 866,571 code, 82,515 comments, 161,111 blank, across 3,414 files in 39 languages (top language: C++ 43.7%). Canonical public options (tests, docs and generated files excluded). Counted with tokei via OctoCounts.
OctoCounts produced this report by resolving ggml-org/llama.cpp to commit 8bfd64b5ac86, downloading the repository source archive, and counting files selected by the effective rules with tokei, the open-source line counter written in Rust. The table below breaks the count down by programming language into files, total lines, code lines, comment lines, and blank lines, so the figures can be compared across languages and projects. Results are cached by commit, tokei version, and analysis options; an exact reproduction needs the same commit, engine version, and effective counting rules.
This is a large codebase by counted code lines. Code represents 78.1% of all lines, comments represent 7.4%, and the repository averages 254 code lines per file. C++ accounts for 43.7% of counted code.
| Language | Files | Lines | Code | Comments | Blanks |
|---|---|---|---|---|---|
| C++ | 695 | 473802 | 379109 | 27916 | 66777 |
| C | 100 | 92877 | 73646 | 4295 | 14936 |
| Python | 206 | 77986 | 62151 | 4032 | 11803 |
| C Header | 334 | 83388 | 59647 | 9862 | 13879 |
| OpenCL | 275 | 59880 | 52172 | 0 | 7708 |
| TypeScript | 386 | 53285 | 34144 | 10988 | 8153 |
| HTML | 2 | 35137 | 25476 | 0 | 9661 |
| JavaScript | 15 | 38332 | 25476 | 9688 | 3168 |
| CUDA | 209 | 31267 | 25434 | 1517 | 4316 |
| GLSL | 195 | 26927 | 21781 | 888 | 4258 |
| JSON | 11 | 21649 | 21640 | 0 | 9 |
| C++ Header | 87 | 21757 | 16815 | 1690 | 3252 |
Top language: C++ 43.7%. Generated on .
ggml-org/llama.cpp: tokei-15.0.0, policy directories-v1; docs excluded, tests excluded, generated excluded. Excluded directory names: .cache, .generated, .git, .next, __tests__, build, dist, doc, docs, documentation, fixtures, gen, generated, node_modules, target, test, tests, vendor. Ignored languages: none. Repository declarations: off. Exclusions are rule-based; they do not prove that every test, document or generated file was removed.
Saved reports remain subject to cache cleanup and replacement. Export the JSON or text for durable citation; live repository URLs can change.
ggml-org/llama.cpp has 866,571 lines of code, plus 82,515 comment lines and 161,111 blank lines, for 1,110,197 total lines at commit 8bfd64b5ac86 on November 16, 2026. Tests, docs and generated files are excluded under OctoCounts' canonical public options.
OctoCounts resolved the public GitHub repository to commit 8bfd64b5ac86, downloaded the source archive, counted it with tokei, and cached the report by commit, tokei version, and analysis options.
This OctoCounts report was generated from master at commit 8bfd64b5ac86 on November 16, 2026.
Play the growth animation for ggml-org/llama.cpp on this page — 866,571 code lines across 39 languages, counted by tokei.