---
title: README
emoji: 📈
colorFrom: indigo
colorTo: gray
sdk: static
pinned: false
---

# GGML - AI at the edge

ggml is a tensor library for machine learning to enable large models and high performance on commodity hardware. It is used by [llama.cpp](https://github.com/ggerganov/llama.cpp) and [whisper.cpp](https://github.com/ggerganov/whisper.cpp)

Written in C
- 16-bit float support
- Integer quantization support (e.g. 4-bit, 5-bit, 8-bit)
- Automatic differentiation
- Built-in optimization algorithms (e.g. ADAM, L-BFGS)
- Optimized for Apple Silicon
- On x86 architectures utilizes AVX / AVX2 intrinsics
- Web support via WebAssembly and WASM SIMD
- No third-party dependencies
- Zero memory allocations during runtime
- Guided language output support