llama.cpp
ToolsLibrary written in C++ to run LLM models on consumer CPUs and GPUs. It is the underlying engine for many local inference tools, including Ollama. It supports GGUF quantization and can run large models on limited hardware by leveraging both CPU and GPU.
Related articles
- Ollama vs llama.cpp: sotto il cofanoComparisons · 7 October 2026 · 6 min read
- ML Drift: il motore GPU on-device open source di Google, e quando batte i generalistiComparisons · 3 November 2026 · 5 min read
- Kolibri di Aleph Alpha: il MoE da 78B che gira (quasi) in localeModels · 18 October 2026 · 7 min read