Notes 
Ollama lets you download and run large language models locally via a simple CLI and REST API. Supports a growing library of open models including Llama, Mistral, and Gemma on Windows, Mac, and Linux with no data sent to the cloud.
Reviewed by Marcus Holmberg
Ollama
ollama.com 4.6 (8)
Rate Ollama: No account needed
Threat level
Hardened
A hardened pick. Worth the effort once you have chosen to shrink your footprint on purpose. Enough for most people. Threat levels
Our take
The clearest on-ramp to local AI: one command pulls a model, a second starts a chat, and nothing leaves your machine. The REST API makes it easy to wire into other tools or build small apps on top. The catch is hardware: capable models need a modern GPU and several gigabytes of RAM, so older or low-spec machines will struggle. For anyone with decent hardware who wants private AI inference without managing Python environments, Ollama is the obvious starting point.
GitHub at a glance
ollama/ollama MIT deepseekgemmaglmgogolanggpt-ossllamallmllmsminimaxmistralmuseollamaqwen
Stars
185,837
+786 this week
Forks
18,872
1,023 watching
Last commit
today
healthy
Latest release
v0.40.14
1d ago, 100+ total
Star history
Issues
77% closed
2,614
open
8,916
closed
+207 / -122
opened / closed, last 4 weeks
Opened vs closed, last 12 weeks
Commits, last 26 weeks
573 commits, active 26 of 26 weeks
446 contributors since Jun 2023
Languages
- Go 73.2%
- C 18.7%
- TypeScript 4.8%
- Other 3.3%
Updated daily from the GitHub API. Star tracking since Jun 22, 2026.
Website at a glance
ollama.com
C score 50
Basic website security headers
Graded by Mozilla HTTP Observatory, tested today
Inspect this site yourself
Measures the security configuration of the tool's own website, not the privacy of the product itself. A strong tool can still score low here.
Ollama alternatives
Lumo Proton's hosted AI assistant with zero-access encryption of saved chats and a strict no-logs policy.
Duck.ai DuckDuckGo's private AI chat that lets you talk to multiple models with no account and no training on your prompts.
Euria Infomaniak's Swiss-hosted AI assistant that pledges no training on user data and operates under GDPR and Swiss data law.
Apple Intelligence Apple's AI. On-device where it can, with verifiable Private Cloud Compute for the rest.
Skales Skales is a local AI desktop agent that runs on your computer with any AI provider you choose. All conversations and data stay on your machine, and you control which model and which API keys you use.
llamafile A Mozilla project that packages a complete LLM and its runtime into a single executable file. Download one file, run it on Windows, Mac, or Linux with no installation, no dependencies, and no network connection required.
Ollama license, in plain English
MIT Permissive
Do almost anything: use, change, and ship it, even inside closed-source products. The only condition is keeping the copyright notice.
Permits
- Commercial use
- Modification
- Distribution
- Private use
Requires
- License and copyright notice
Does not provide
- Liability cover
- Warranty
Why it matters: Permissive licensing lets anyone reuse this, including inside closed products. That is freedom to build on, but no guarantee that downstream copies stay open.
Plain-language summary of the project's license, not legal advice. Read the full text for the exact terms.