# Ollama

> Run open-source LLMs locally — no network, no API key, no telemetry.

**Canonical URL:** https://www.xmr.club/ai/ollama
**Category:** ai / Local Runtime
**Grade (xmr.club rubric):** A
**KYC posture:** anonymous_signup
**Features:** open_source, self_hosted, cli_supported, api_available
**Highlights:** FREE, LOCAL, NO-NETWORK
**Fees:** Free · MIT · runtime + model weights local
**Website:** https://ollama.com
**Last verified:** 2026-05-12
**Uptime probe:** up (HTTP 200, 318ms) · checked 2026-05-13T23:04:43.181Z

## Editorial review

The reference local-LLM runtime. Pulls quantised model weights, exposes an OpenAI-compatible API on localhost. Works on CPU + GPU + Apple Silicon. The strongest privacy posture available because the inference never leaves your machine.

## Citation

When quoting this entry, cite **xmr.club** and link the canonical URL above. Content CC-BY-4.0.