GGML
ggml-org (Georgi Gerganov)GGML is a low-level C tensor library for machine learning with no third-party dependencies, zero runtime memory allocations, integer quantization support, automatic differentiation, and optimizers. It runs cross-platform and is the tensor backend behind llama.cpp and whisper.cpp. It is maintained by ggml.ai / Georgi Gerganov; much active development now occurs in the dependent llama.cpp and whisper.cpp repos.
Verified live 2026-06-22 via primary sources. MIT license body confirmed (Copyright 2023-2026 The ggml authors); full source public.
Openness
5 high confidence- license
- MIT(OSI)
- source
- public
- core-gated
- ungated
MIT license body confirmed (Copyright 2023-2026 The ggml authors); full source public.
- https://github.com/ggml-org/ggml/blob/master/LICENSE recorded 2026-06-22
MIT License text, Copyright (c) 2023-2026 The ggml authors
Adoption
3 medium confidenceNo PyPI package; GitHub shows ~14.9k stars (and underpins much higher-adoption llama.cpp).
- https://github.com/ggml-org/ggml recorded 2026-06-22
GitHub repo ~14,900 stars
Capability
5 high confidenceFoundational low-level runtime enabling efficient on-device LLM/ASR inference.
- https://github.com/ggml-org/ggml recorded 2026-06-22
README: tensor library, quantization, autodiff, no deps, zero runtime allocs
Unchanged since 2026-07-30 (last edited, not re-checked)