GGML

GGML is a low-level tensor library for machine learning designed to enable large models and high performance on commodity hardware. It is the engine behind llama.cpp and whisper.cpp. The library features integer quantization support, broad hardware support, no third-party dependencies, and zero memory allocations during runtime. GGML is minimal and open core, available under the MIT license, with a development process that is open to everyone. The company behind GGML, ggml.ai, was founded in 2023 and acquired by Hugging Face in 2026.

Key Benefits

• Minimal and simple codebase
• Open core under MIT license
• Integer quantization support
• Zero memory allocations during runtime