# ggml-org/llama.cpp SLOC report

> As of 2026-09-14 (commit 7cf1c54a96d4), ggml-org/llama.cpp contains 934,298 total lines: 722,120 code, 73,304 comments, 138,874 blank, across 2,924 files in 40 languages (top: C++ 43.6%). Custom configuration (tests excluded, docs excluded, generated excluded). Counted with tokei via OctoCounts.

ggml-org/llama.cpp has 722,120 source lines of code out of 934,298 total lines across 2,924 files, counted from the 7cf1c54a96d4e950ffa614b94babf762803a8de7 ref at commit 7cf1c54a96d4 by the OctoCounts tokei engine on 2026-09-14. The report is cached by commit, tokei version, and analysis options, so recounting the same revision returns exactly these numbers.

OctoCounts produced this report by resolving ggml-org/llama.cpp to commit 7cf1c54a96d4, downloading the repository source archive, and counting every source file 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, so counting the same revision again reproduces exactly these numbers.

## Repository size insights

This is a large codebase by counted code lines. Code represents 77.3% of all lines, comments represent 7.8%, and the repository averages 247 code lines per file. C++ accounts for 43.6% of counted code.

| Language | Files | Lines | Code | Comments | Blanks |
| --- | ---: | ---: | ---: | ---: | ---: |
| C++ | 609 | 397,684 | 315,025 | 24,438 | 58,221 |
| C | 90 | 76,147 | 59,616 | 4,055 | 12,476 |
| Python | 174 | 61,502 | 48,528 | 3,456 | 9,518 |
| C Header | 282 | 67,389 | 47,202 | 8,711 | 11,476 |
| OpenCL | 179 | 44,250 | 38,492 | 0 | 5,758 |
| TypeScript | 323 | 42,604 | 27,189 | 9,062 | 6,353 |
| HTML | 2 | 35,137 | 25,476 | 0 | 9,661 |
| JavaScript | 15 | 38,328 | 25,476 | 9,684 | 3,168 |
| JSON | 11 | 21,243 | 21,234 | 0 | 9 |
| CUDA | 189 | 25,690 | 20,661 | 1,262 | 3,767 |
| GLSL | 187 | 22,853 | 18,290 | 803 | 3,760 |
| C++ Header | 80 | 19,585 | 15,098 | 1,506 | 2,981 |

Top language (C++ 43.6%). Generated at 2026-09-14T20:56:50.397098328+00:00. Canonical report: https://octocounts.com/github/ggml-org/llama.cpp

## Reproduce this report

[Reproduce this exact report and configuration](https://octocounts.com/github/ggml-org/llama.cpp/commit/7cf1c54a96d4e950ffa614b94babf762803a8de7?analysis=%7B%22ignoredDirs%22%3A%5B%5D%2C%22ignoredLanguages%22%3A%5B%5D%2C%22profile%22%3A%22default%22%2C%22includeDocs%22%3Afalse%2C%22includeTests%22%3Afalse%2C%22includeGenerated%22%3Afalse%7D).

## Report FAQ

### How many lines of code does ggml-org/llama.cpp have?

ggml-org/llama.cpp has 934,298 total lines, including 722,120 code lines, 73,304 comment lines, and 138,874 blank lines.

### How was the ggml-org/llama.cpp line count measured?

OctoCounts resolved the public GitHub repository to commit 7cf1c54a96d4, downloaded the source archive, counted it with tokei, and cached the report by commit, tokei version, and analysis options.

### What commit was counted for ggml-org/llama.cpp?

This OctoCounts report was generated from 7cf1c54a96d4e950ffa614b94babf762803a8de7 at commit 7cf1c54a96d4 on 2026-09-14T20:56:50.397098328+00:00.

## Similar repository reports

- [PrismML-Eng/llama.cpp](https://octocounts.com/github/PrismML-Eng/llama.cpp) — C++, 700,092 code lines
- [ARM-software/kleidiai](https://octocounts.com/github/ARM-software/kleidiai) — C++, 635,456 code lines
- [AyuGram/AyuGramDesktop](https://octocounts.com/github/AyuGram/AyuGramDesktop) — C++, 840,188 code lines
- [OpenRCT2/OpenRCT2](https://octocounts.com/github/OpenRCT2/OpenRCT2) — C++, 854,277 code lines
- [protocolbuffers/protobuf](https://octocounts.com/github/protocolbuffers/protobuf) — C++, 871,834 code lines
- [apache/trafficserver](https://octocounts.com/github/apache/trafficserver) — C++, 880,616 code lines

## Related OctoCounts pages

- [Recently analyzed repositories](https://octocounts.com/recent)
- [Popular SLOC reports](https://octocounts.com/popular)
- [Trending GitHub repositories](https://octocounts.com/trending)
- [Hall of Monoliths](https://octocounts.com/hall-of-monoliths)
- [TensorFlow vs PyTorch](https://octocounts.com/compare/tensorflow-vs-pytorch)
- [Electron vs Tauri](https://octocounts.com/compare/electron-vs-tauri)
- [Godot vs Bevy](https://octocounts.com/compare/godot-vs-bevy)
- [GitHub SLOC counter guide](https://octocounts.com/docs/github-sloc-counter)
- [Counting methodology](https://octocounts.com/docs/methodology)
- [SLOC and code metrics glossary](https://octocounts.com/docs/glossary)
- [Original research: how filtering changes SLOC counts](https://octocounts.com/research)
- [OctoCounts API docs](https://octocounts.com/docs/api)