# ggml

19 Hacker News commenters recommended ggml and 1 criticized it, November 2025 to November 2026. It was recommended in 6 of 13 months. It meets the Hacker Approved badge rule.

**Verdict:** Small, portable C/C++ tensor library that people rely on to run local AI models, praised for its openness and quantization work.

## Why people recommend it

- Deserves sustained financial support (3 comments): "I have always worried about ggml and long term prospect for them and wished for them to be rewarded for their effort." ([source](https://news.ycombinator.com/item?id=47089042)) "I've been sponsoring ggml/llama.cpp/Georgi since 2023 via Github." ([source](https://news.ycombinator.com/item?id=47089605)) "consistent reliable economic support" ([source](https://news.ycombinator.com/item?id=47089643))
- Open source and quantization contributions (3 comments): "They did so much work for quantization and actually made it available to everyone." ([source](https://news.ycombinator.com/item?id=47095842)) "GGML & GGUF have been extremely important to the open-source ML/AI space" ([source](https://news.ycombinator.com/item?id=48142110)) "I like the openness of both project" ([source](https://news.ycombinator.com/item?id=47088233))
- Small, portable, fits local inference (2 comments): "Keeping inference in bare-metal C/C++ without the Python bloat is the only way local AI is going to scale efficiently." ([source](https://news.ycombinator.com/item?id=47099906)) "ggml turned out to be a great fit for this as it's small, portable" ([source](https://news.ycombinator.com/item?id=48278510))
- Respected and easy to learn (3 comments): "ggml, which is about as hardcore as it gets in the LLM space" ([source](https://news.ycombinator.com/item?id=49417732)) "Finally someone who pays proper respect to GGML ecosystem." ([source](https://news.ycombinator.com/item?id=48060359)) "is really easy, educational and fun to use" ([source](https://news.ycombinator.com/item?id=48907786))

## Alternatives hackers recommend

- [PyTorch](https://hackerapproved.com/p/pytorch.md): 131 recommend
- [MLX](https://hackerapproved.com/p/mlx.md): 75 recommend
- [JAX](https://hackerapproved.com/p/jax.md): 49 recommend
- [OpenCV](https://hackerapproved.com/p/opencv.md): 46 recommend
- [tinygrad](https://hackerapproved.com/p/tinygrad.md): 40 recommend

## Cite as

Hacker Approved, "ggml", https://hackerapproved.com/p/ggml/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).