AI People Wiki

Builders & open source

Georgi Gerganov

Maintains llama.cpp with the ggml team, Hugging Face

Georgi Gerganov develops ggml, a tensor library for machine learning on commodity hardware, and llama.cpp, a C/C++ runtime for running language models locally. Gerganov's site also lists whisper.cpp, which runs OpenAI's Whisper speech recognition model on the CPU. Gerganov founded ggml.ai in 2023 to support ggml development, and Hugging Face acquired the company in 2026. Hugging Face's announcement says the ggml team still spends all of its time maintaining llama.cpp and keeps full leadership of the project's technical direction.123

At a glance

Current role
Maintains llama.cpp with the ggml team
Sector
Company
Work listed
3
Sources cited
11
Profile reviewed

Open-source work

Gerganov made the initial-release commits of three related repositories now hosted under the ggml-org organization on GitHub. The first was ggml, a tensor library for machine learning, in September 2022; ggml's site describes it as a low-level, cross-platform library with integer quantization, broad hardware support, no third-party dependencies and no memory allocations during runtime. A week later Gerganov released whisper.cpp, a C/C++ port of OpenAI's Whisper speech recognition model.5627

Gerganov's initial release of llama.cpp on 2023-03-10 contained ggml, a model conversion script, a quantization tool and a main program for running the model. The project's README describes its goal as running language and vision-language model inference with minimal setup across a wide range of hardware, locally and in the cloud, in plain C/C++ built on the ggml library. All three projects are MIT-licensed.892

Gerganov remains an active maintainer of llama.cpp. The repository's CODEOWNERS file lists Gerganov as an owner for many core areas, and Gerganov authored commits to the project in October 2026.1011

ggml.ai and Hugging Face

Gerganov founded ggml.ai in 2023 to support the development of ggml, and the company states that the library and related projects are freely available under the MIT license with an open development process. ggml.ai was acquired by Hugging Face in 2026.2

Hugging Face announced on 2026-02-20 that GGML, the creators of llama.cpp, were joining the company, and that Gerganov and team would join it. The announcement says the team keeps full autonomy and leadership over the project's technical direction and community, and that planned work includes making it easier to bring new models from the transformers library to llama.cpp. Gerganov's GitHub profile lists Hugging Face as the current company.34

Work and contributions

  • llama.cpp

    Listed among the projects on Gerganov's site and announced by Hugging Face as the ggml team's project. The repository's CODEOWNERS file names Gerganov for core areas including the CPU and Metal backends, quantization code, and llama-server, and Gerganov continues to author commits to it.131011

  • ggml

    Founded ggml.ai in 2023 to support development of ggml, the tensor library with integer quantization support that llama.cpp and whisper.cpp are built on. The library is MIT-licensed.2

  • whisper.cpp

    Listed on Gerganov's site as inference of OpenAI's Whisper speech recognition model on the CPU, and pinned on Gerganov's GitHub profile as a C/C++ port of the model.14

Timeline

  1. Made the initial-release commit of the ggml tensor library.5
  2. Made the initial-release commit of whisper.cpp, a C/C++ port of OpenAI's Whisper model.67
  3. Founded ggml.ai to support development of the ggml library.2
  4. Made the initial-release commit of llama.cpp, including ggml, a conversion script and a quantization tool.8
  5. Hugging Face announced that Gerganov and the GGML team, creators of llama.cpp, were joining the company.3

Other documented roles

Roles the sources document that are not confirmed as current.

  • Founder (2023); the company was acquired by Hugging Face in 2026, ggml.ai2

Where they work

Suggest a correction or removal

Profiles cover public professional work only, and each statement cites a source. If something is out of date, missing or wrong, tell us and link a source. People can also ask for their profile to be corrected or removed.

References

11 sources · profile reviewed Oct 21, 2026 · data updated Oct 21, 2026

  1. Georgi Gerganov — projectsGeorgi Gerganov · Official page · accessed Oct 1, 2026 · reviewed Oct 1, 2026
  2. ggml.ai — about the company and the ggml libraryggml.ai · Official page · accessed Oct 21, 2026 · reviewed Oct 21, 2026
  3. GGML and llama.cpp join HF to ensure the long-term progress of Local AIHugging Face · Announcement · published Feb 20, 2026 · accessed Oct 21, 2026 · reviewed Oct 21, 2026
  4. ggerganov (Georgi Gerganov) on GitHubGitHub · Official page · accessed Oct 21, 2026 · reviewed Oct 21, 2026
  5. ggml-org/ggml — initial release commit (2022-09-18)ggml-org (GitHub repository) · Repository · published Sep 18, 2022 · accessed Oct 21, 2026 · reviewed Oct 21, 2026
  6. ggml-org/whisper.cpp — initial release commit (2022-09-25)ggml-org (GitHub repository) · Repository · published Sep 25, 2022 · accessed Oct 21, 2026 · reviewed Oct 21, 2026
  7. ggml-org/whisper.cpp READMEggml-org (GitHub repository) · Repository · accessed Oct 21, 2026 · reviewed Oct 21, 2026
  8. ggml-org/llama.cpp — initial release commit (2023-03-10)ggml-org (GitHub repository) · Repository · published Mar 10, 2023 · accessed Oct 21, 2026 · reviewed Oct 21, 2026
  9. ggml-org/llama.cpp README (description and supported hardware)ggml-org (GitHub repository) · Repository · accessed Oct 21, 2026 · reviewed Oct 21, 2026
  10. ggml-org/llama.cpp CODEOWNERSggml-org (GitHub repository) · Repository · accessed Oct 21, 2026 · reviewed Oct 21, 2026
  11. ggml-org/llama.cpp recent commits on master (feed)ggml-org (GitHub repository) · Repository · accessed Oct 21, 2026 · reviewed Oct 21, 2026