Ollama iconOllamaGet
Ollama icon

Ollama

Run open LLMs locally on your own machine

Ollama Inc. · Development

CheckedFree · open source
Get — Official Source

Link verified · points to the developer’s official site

Rating

—

No public ratings yet

Trust

7/9

of nine checks verified · Jul 19, 2026

Platforms

1

macOS, Windows, Linux

Licence

MIT

Development

Ollama screenshot 1 of 3
Ollama screenshot 2 of 3
Ollama screenshot 3 of 3

Trust Report

See Details ›

Independently checked by Altapp where possible; developer-reported data is labeled as such. Last full review: Jul 19, 2026.

Verified Source

Open source under the MIT license, with all code developed in the open on GitHub.

  • Source code fully public at github.com/ollama/ollama
  • MIT licensed — free to inspect, modify, and self-host
  • Published by Ollama Inc., based in the United States
  • No independent third-party security audit is publicly documented

Data & Permissions

Runs models entirely on your device; local use needs no account and no internet after download.

  • Local models run 100% on-device and work fully offline once downloaded
  • No account required to install or run local models
  • Prompts and responses from local models are not collected or used for training
  • Optional cloud (-cloud) models send content to Ollama servers, processed transiently and not stored (per privacy policy)

Known Risks

A few things to weigh before relying on it.

  • Build signing and notarization are not independently verified here
  • Past CVEs (e.g. CVE-2024-37032, CVE-2026-7482) required network access to the API, which has no built-in authentication — keep it bound to localhost
  • Optional cloud (-cloud) models send prompts off-device; only local models are fully offline
  • A paid cloud tier now exists, though the core local app remains free and open source

Verification reflects the version listed above. Practices may change between releases. How we verify ›

Our verdict: the most straightforward way to run open LLMs entirely on your own machine — private by default, needing no account and no cloud, with signing and audit status we could not independently confirm.

Ollama is an open-source tool that lets you download and run open large language models — including Llama, Gemma, Qwen, DeepSeek and gpt-oss — 100% locally on your own hardware. A single command pulls a model from its 200+ model library and runs it, with GPU acceleration on NVIDIA, AMD and Apple Silicon.

Because local models run entirely on-device, Ollama works offline once a model is downloaded, and its privacy policy says prompts and responses from local models are not collected or used for training (limited usage metadata such as app version may be). It is a CLI-first tool that also ships a desktop chat app for macOS and Windows, plus a local REST API with OpenAI- and Anthropic-compatible endpoints. Optional cloud models are reachable through the same API, but those send content to Ollama's servers.

Member reviews

LinkedIn-verified members

No reviews yet — be the first.

Loading…

Frequently asked questions

Is Ollama free?

Yes — the pricing listed at our last review is “Free · open source”.

Is Ollama safe to use?

Altapp's independent Trust Report (last full review Jul 19, 2026) records 7/9 of nine checks verified, covering source verification, data & permissions, and known risks. Altapp publishes no score or grade of its own — the count is a tally of what could be independently confirmed, and verification reflects the version listed on this page.

Which platforms does Ollama run on?

macOS · Windows · Linux.

Where can I find Ollama alternatives?

Browse the Development category on Altapp for verified options.

Information

Developer
Ollama Inc.
Size
—
Category
Development
Compatibility
macOS · Windows · Linux
Languages
English
License
MIT
Country
United States
Latest Version
0.40.11 · Oct 2026