PROJECT LANDSCAPE

Find tools — and ways to get involved

Project profiles go beyond links: licenses, support matrices, maintenance status, benchmarks and first-contribution tasks.

⌕

Inference engine · Active

llama.cpp

A high-performance local inference engine for broad hardware and the GGUF ecosystem.

Model runtime · Active

Local model running, management and API serving for developers.

Cross-platform · Active

Deploy models to desktop, mobile, browser and GPU via ML compilation.

Open call

Use a unified template to add a compatibility matrix, license, quick start and contribution entry points.