llama.cpp
LLM inference in C/C++ open source
Where it ranks
- Run LLMs locally: Runner-up (74/100)
Pricing
Open source.
Source: https://github.com/ggml-org/llama.cpp, checked 2026-10-19
Public signals
| GitHub stars | 132ksource |
|---|---|
| Forks | 24.6k |
| Last push | Oct 19, 2026 |
| 7-day star change | unknown (needs 7 days of snapshots) |
| Latest stable release | b11742 Oct 19, 2026 |
| Hacker News, last 30 days | 0 stories, 0 points query |
Matched by linked URL “github.com/ggml-org/llama.cpp”. Title matches can include unrelated stories.
Recent releases
- b11742 Oct 19, 2026
hybrid dna tokenizer fixes ( #30825 ) vocab : support Carbon-14B HybridDNA tokenizer Carbon-14B auto-tags untagged DNA runs and uses N-padded tail tokens (tail=pad_n). Also strip whitespace inside tags and handle a stray like the HF tokenizer. convert : fix special tokens and mer - b11741 Oct 19, 2026
opencl: add cooperative-k dp4a gemm for q4_0, q4_k and q6_k ( #30741 ) opencl: add cooperative-k dp4a GEMM for q4_0 opencl: add cooperative-k dp4a GEMM for q4_k opencl: add cooperative-k dp4a GEMM for q6_k opencl: fix alignment Website: https://llama.app Attestations: https://git - b11740 Oct 19, 2026
opencl: add get_rows for i32, cpy for i32 and f32 ( #30756 ) opencl: support i32 GET_ROWS opencl: support i32 and f32 copy conversions Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/57528236 macOS/iOS: macOS Apple Silicon (arm64) macOS