Ollama
by Ollama
At a glance
Open-source tool for running open large language models locally on your own machine with a simple command-line interface.
local-llm open-source inference
- Licence
- MIT
- Category
- Platforms & Infrastructure
- Business model
- Open (open weights/source)
- Availability
- Global
- Launched
- 2023-07
Overview
Ollama is a platforms product from Ollama, a US company founded in 2023: an open-source (MIT-licensed) tool for running open large language models locally. You self-host it on your own machine as a command-line tool, with documented install paths for Linux, macOS and Windows plus Docker, and it exposes a local REST API that other apps can call. No material change was found in this review. The main limitation is that offline operation is only partial: a network connection is still needed to download models, and the record does not state the product's own interface languages.
Compare this tool Suggest a correction
Key features
- One-command download and run for popular open models
- Local REST API compatible with many client apps
- Model library with quantized variants for consumer hardware
- Cross-platform support including GPU acceleration
Use cases
- Private, offline AI chat and coding assistance
- Local development against an LLM API without cloud costs
- Experimenting with and comparing open models
Pricing
Ollama is free and open source; optional hosted services are offered separately.
Record details
Provenance, dates and links are kept here so the main sections stay about the product itself.
Links, dates and provenance
- Record updated
- 2026-10-10
- Pricing
- ollama.com ↗
- Documentation
- docs.ollama.com ↗
- Founded
- 2023
- Headquarters
- US
- Canonical URL
- https://globalaiproductindex.com/products/ollama/
Selection profile
Every field says where its value comes from. "Unknown" means we have not confirmed it — it does not mean the product lacks the feature.
Selection profile11 fields1 unknown
- Tasks it fits
- Running models yourself
Derived from the record: category "platforms".
Suggest a correction - How you use it
- Self-run service
Open-source project without a tag describing its delivery form; run it yourself.
Suggest a correction - Runs on
- Linux macOS Windows
Linux, macOS, Windows and Docker install paths are documented.
Suggest a correction - Where it runs
- Local machine
Record tags a local/on-device model runtime.
Suggest a correction - Works offline
- Partly
Local execution implies the model can run without a network once downloaded, but the vendor does not state this in the record.
Suggest a correction - Official service region
- Global
Mirrors the availability field already on the record ("global").
Suggest a correction - Public API
- Yes
Docs navigation publishes an API Reference.
Suggest a correction - Licence
- MIT
Mirrors the licence already recorded on the product record; not re-verified against the licence text by this migration.
Suggest a correction - Commercial use
- Permitted
Recorded licence allows commercial use (copyleft obligations may still apply).
Suggest a correction - Interface languages
- Not recorded
No vendor page read in this pass states the product's own interface languages; the key exists so the field can be answered later rather than left absent.
Suggest a correction - Billing
- Free Subscription USD 20/month Free allowance: Yes Subscription required: No
Prices are the vendor’s advertised entry price and exclude taxes; always confirm on the vendor’s own page.
Suggest a correction
Where each value comes from
- Tasks it fits
- Our inference
- How you use it
- Our inference
- Runs on
- Verified 2026-10-10 docs.ollama.com ↗
- Where it runs
- Our inference
- Works offline
- Our inference
- Official service region
- Our inference
- Public API
- Verified 2026-10-10 docs.ollama.com ↗
- Licence
- Our inference
- Commercial use
- Our inference
- Interface languages
- Unknown
Key facts and their evidence
Each fact lists the conditions it holds under, the page it was read from and the day it was checked.
-
Platform support: windows, macos, linux Verified 2026-10-09 docs.ollama.com ↗
Applies to: As stated on docs.ollama.com on 2026-10-09
Matched on the vendor page: “ormation CLI Reference Modelfile Reference Context length Linux macOS Windows Docker Importing a Model FAQ Hardware support Troubleshooting Sign in Download Guide Integra”
Suggest a correction -
API: Public API documented Verified 2026-10-09 docs.ollama.com ↗
Applies to: As stated on docs.ollama.com on 2026-10-09
Matched on the vendor page: “Hardware support Troubleshooting Sign in Download Guide Integrations API Reference Ollama home page Search... ⌘ K Sign in Download Download Search... Navigation Get star”
Suggest a correction -
Pricing: Free tier with starter models; usage beyond it is paid by adding credits, with no service fee Verified 2026-10-10 ollama.com ↗
Applies to: Individual account
Suggest a correction -
Pricing: 20 USD/month Verified 2026-10-10 ollama.com ↗
Applies to: Pro plan billed monthly; the same plan is $200/year
Suggest a correction -
Pricing: 100 USD/month Verified 2026-10-10 ollama.com ↗
Applies to: Max plan, for running several agents at once
Suggest a correction -
Pricing: 500 USD/month Verified 2026-10-10 ollama.com ↗
Applies to: Team plan: unlimited users and $1,000 of monthly usage credits
Suggest a correction -
API: yes Verified 2026-10-10 docs.ollama.com ↗
An API Reference is published in the docs navigation.
Suggest a correction -
Platform support: linux, macos, windows Verified 2026-10-10 docs.ollama.com ↗
Docs list Linux, macOS and Windows install paths plus Docker.
Suggest a correction
Frequently asked questions
Is Ollama free?
Yes. Ollama is free, open-source software for running models locally.
Which models does Ollama support?
Ollama runs popular open models including Llama, Qwen, Gemma, Mistral, and DeepSeek in quantized local formats.
Does Ollama need internet access?
Only for downloading models; once downloaded, models run fully offline on your machine.
Who should not choose Ollama?
People without the hardware to run models locally, or who want a fully managed cloud service, should not choose Ollama: it requires your own machine, and a network connection is needed to download models.
Similar products
- LM Studio — Desktop application for discovering, downloading, and running open large language models locally.
- Jan — Open-source desktop app for running open language models locally as an offline ChatGPT alternative.
- Open WebUI — Extensible, self-hosted AI interface that runs offline and connects to local or remote models such as Ollama and OpenAI-compatible APIs.
- vLLM — Open-source inference and serving engine for large language models, known for high-throughput PagedAttention.
- Llama — Open-weight large language model family from Meta, spanning Llama 3 and Llama 4 generations across multiple sizes.
- Baseten — Platform for deploying and serving machine-learning models as scalable APIs.
All Ollama alternatives → · All Platforms & Infrastructure products →
Related comparisons
Related guides
Sources
This record was last reviewed on 2026-10-10.
Machine-readable record: /api/products/ollama.json · Spot an error? Suggest a correction