LLM Reference
Concepts & capability filters

GPT-Generated Machine Learning

GGML is a low-level C tensor library for machine-learning inference on commodity CPUs and GPUs — the engine underneath local runtimes like llama.cpp, not a model format you choose directly.

Category
Not classified
Difficulty
Not classified
Aliases
None tracked
Last reviewed
2026-07-02

Key facts

  • For self-hosting decisions you interact with it indirectly; the file format to pick is GGUF, which GGML-based runtimes load.