Ollama
Software
Inference
Active
One command to run an open model locally.
You're looking at a software record: a tool or platform in the AI stack — who maintains it and what hardware it runs on.
Ollama wraps llama.cpp in a polished model manager — pull, run, serve — and became the front door through which millions of developers first ran Llama, Qwen or Gemma on their own machines.
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Related
Sources
Record reviewed as of 2026-01-15 — see Methodology.