Vibeleaderboard
← Back to Vibers
ggml-org
Company

ggml-org

Index Rank19
github.com/ggml-org

6 Tools · 1 Intel

ggml-org is the GitHub organization of Georgi Gerganov, a Bulgarian software engineer who left a career in medical physics and radiation therapy at ViewRay to build open-source machine learning infrastructure focused on running large AI models efficiently on commodity hardware. His company ggml.ai — seeded by Nat Friedman and Daniel Gross in 2023 — joined Hugging Face in early 2026, keeping all projects fully open-source under the MIT license.

Tools

llama.cpp(github.com/ggml-org/llama.cpp)

C/C++ library for running LLM inference locally on CPUs and GPUs, with quantization options to cut memory use.

AI ToolsOpen SourceLLM Infrastructure★ 127.5kMITbuilt by ggml-org
ggml(https://github.com/ggml-org/ggml)

Tensor library in pure C with no dependencies, sitting under llama.cpp, whisper.cpp, and on-device inference.

AI ToolsOpen SourceLLM Infrastructure★ 15.3kMITbuilt by ggml-org
llama.vim(https://github.com/ggml-org/llama.vim)

Vim plugin for LLM-assisted code and text completion, running locally through llama.cpp with no cloud dependency.

Developer ToolsOpen SourceSkills & Plugins★ 2.2kMITbuilt by ggml-org
LlamaBarn(https://github.com/ggml-org/llamabarn)

Swift-built macOS app for managing and running local llama.cpp language models from the desktop.

AI ToolsOpen SourceLLM Infrastructure★ 1.5kMITbuilt by ggml-org
llama.vscode(https://github.com/ggml-org/llama.vscode)

VS Code extension providing local LLM-assisted code and text completion powered by llama.cpp.

Developer ToolsOpen SourceSkills & Plugins★ 1.5kMITbuilt by ggml-org
p1(https://github.com/ggml-org/p1)

Local-first code completion engine from the ggml team that runs small models for editor autocomplete.

AI ToolsOpen SourceLLM Infrastructure★ 194built by ggml-org

Intel

llama.cpp v0.4.0(github.com/ggml-org/llama.cpp)

llama.cpp's 0.4.0 release adds initial Qwen3.8-Flash-Next and Nemotron-3-Puzzle-75B-A9B model support, on-demand tensor reading, per-slot server context limits, video input options, and a ggml bump with sparse flash attention and RDMA work.

AI Toolsbuilt by ggml-org