# ggml-org/ggml

> A dependency-free C/C++ tensor library for machine learning with quantization and support for CPU, GPU, NPU, and WebAssembly. It serves as a foundation for running ML models across platforms with minimal setup.

- Magnitude: 6.7 out of 10 — Breakout
- Stars: 15,727 total · +101 stars measured 2026-11-14, 03:35–10:32 UTC, ≈ 185 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: C++ · License: MIT · Created: 2022-09-18 · Last push: 2026-11-13
- GitHub: https://github.com/ggml-org/ggml · Homepage: https://github.com/ggml-org · Page: https://gitnova.dev/en/r/ggml-org/ggml

## Useful for

- Build the library from source with CMake for use in a C++ project
- Run the examples/simple example to learn matrix multiplication
- Apply 2-8-bit quantization to reduce tensor memory footprint

## How to get started

```sh
git clone https://github.com/ggml-org/ggml
cd ggml

mkdir build && cd build
cmake ..
cmake --build . --config Release -j 8
```

Copied as is from the “quick start” section of the README. GitNova has not run these commands: check them in the original before running: https://github.com/ggml-org/ggml#readme

## Why it’s here

- Star-counter measurements on 2026-11-14 (UTC), 03:35–10:32: 15626 → 15727 stars (+101). This is the change over that interval.
- Estimated end-of-day forecast: about +185 stars, using observed gains and the previous day.
- Over the last two days the pace is 26× that of the previous week and a half.
- Hacker News: “Ggml v1.0.0” — 267 points, 8 h ago.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 1,944
- Issues and pull requests: 1,538
- Watchers: 150
- Average over the last week: 42 per day
- Usual pace: 5 per day
- Stars in the last hour (measured): 14
- Latest release: v1.0.0 (2026-11-13)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-16 … 2026-11-14: 4, 5, 8, 7, 4, 2, 4, 2, 7, 12, 6, 4, 8, 4, 7, 2, 9, 6, 2, 5, 5, 4, 5, 8, 3, 7, 3, 2, 90, 101

## Hacker News

- Ggml v1.0.0 — 267 points, 43 comments: https://news.ycombinator.com/item?id=50493062

## Spotted in now

- Spotted on Hacker News

## More in this category

1. **hyperionaidev/smolmaxxing** — 6.8 · Early signal · Language models · C · +23 stars measured 2026-11-14, 00:03–10:32 UTC, ≈ 115 by evening
   A project for running LLMs on low-power devices (TV boxes, old tablets, SBCs) with ARM-specific optimizations: custom kernels, weight streaming, MoE expert paging. The goal is to squeeze maximum tokens per second out of devices with 1-2…
   Full card: https://gitnova.dev/en/r/hyperionaidev/smolmaxxing.md
2. **Edge0-AI/Edge0** — 6.2 · Breakout · Language models · C++ · +385 stars measured 2026-11-14, 00:03–10:32 UTC, ≈ 788 by evening
   An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run model tiers (35B and…
   Full card: https://gitnova.dev/en/r/Edge0-AI/Edge0.md
3. **basetenlabs/deepseek-ultrafast** — 5.9 · Early signal · Language models · Rust · +58 stars measured 2026-11-14, 00:49–10:32 UTC, ≈ 122 by evening
   A high-performance Rust inference engine for DeepSeek-V4.1-Flash on sm_100a/sm_103a GPUs, supporting 1M context and multi-server KV cache sharing.
   Full card: https://gitnova.dev/en/r/basetenlabs/deepseek-ultrafast.md
4. **ggml-org/llama.cpp** — 4.9 · Breakout · Language models · C++ · +85 stars measured 2026-11-14, 00:03–10:33 UTC, ≈ 206 by evening
   LLM and VLM inference implemented in C/C++ with no dependencies, running on CPUs and GPUs across many hardware backends. Enables local model execution with minimal setup and quantization.
   Full card: https://gitnova.dev/en/r/ggml-org/llama.cpp.md
5. **facebookresearch/faiss** — 4.3 · Breakout · Language models · C++ · +18 stars measured 2026-11-14, 00:03–10:33 UTC, ≈ 48 by evening
   A C++ library with Python wrappers for efficient similarity search and clustering of dense vectors, including indexes scaling to billions of vectors and GPU acceleration. Developed at Meta for vector search tasks.
   Full card: https://gitnova.dev/en/r/facebookresearch/faiss.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-14 10:41 UTC, updated every 30 minutes.