DEV TOOLS
An open-source tool for downloading and running open-weight language models on a Mac, Windows or Linux machine, or on your own server. It provides a simple command line, a desktop app and a local API, plus optional paid cloud models for larger workloads.
- PRICE
- Freemium
- SET-UP
- Intermediate
- DATA
- Runs on your device
- FOUNDED
- 2021
- HQ
- Palo Alto, USA
- WEBSITE
- ollama.com
- REVIEWED
- October 2026
SPEC SHEET
001 / WHAT IT DOES
- 01One-command download and running of open-weight models
- 02Local REST API for connecting apps and agents
- 03Desktop apps for macOS, Windows and Linux
- 04Optional cloud models for workloads too large for local hardware
BEST FOR
- Developers prototyping with open models on their own machines
- Organisations needing AI processing to stay on premises
- IT teams building private internal assistants
TYPICAL USES
002 / THE HONEST TAKE
STRENGTHS
- +Free and open source for local use
- +Local processing keeps data on your own hardware
- +Very simple to install and run models
- +Local API works with many developer tools
WATCH OUTS
- –Large models need expensive hardware to run well
- –Open models can trail the strongest hosted models on hard tasks
- –Command-line roots may put off non-technical users
- –Cloud models process data mainly in the United States
003 / FOR AUSTRALIAN BUSINESSES
Works on your own computer, so files can stay local.
In local mode, models run on your own computer or server, so prompts, files and outputs stay on that hardware and nothing is sent to Ollama. Its optional cloud models are hosted mainly in the United States, with possible routing to Europe and Singapore, and Ollama says prompts and responses are not logged or used for training.
PRIVACY ACT & PRACTICAL NOTES
Ollama is one of the simplest ways for an Australian business to keep AI processing on its own hardware. When models run locally, prompts and documents never leave the machine, which removes overseas disclosure questions under APP 8 and suits sensitive work in health, legal and government settings. The trade-off is hardware: larger models need a capable GPU or Apple silicon with plenty of memory. Ollama's cloud models are a different matter, as they run mainly in the United States, so decide which mode staff may use.
004 / WHAT IT COSTS
Freemium
Running models locally is free and open source. Optional cloud plans, Pro, Max, Team and Enterprise, provide usage credits for larger hosted models, concurrency and admin controls, and the free plan includes starter cloud credits. See ollama.com/pricing for current details.
Check current prices on ollama.com ↗︎005 / CONNECTS WITH
Want it wired into your CRM, inbox or Xero? That's what we build.
006 / ALTERNATIVES
Also worth a look
- LM StudioOn deviceFree→
- Hugging FaceOnshore possibleFreemium→
- Google AI StudioOnshore possibleFreemium→
- OpenRouterOffshoreFreemium→
- LangChainAU optionFreemium→
- CohereOnshore possibleFreemium→
- DeepSeekOnshore possibleFreemium→
Also compared against: llama.cpp, Jan, GPT4All.
007 / QUESTIONS
Anything else is quicker to answer on a call. Thirty minutes, free, with the people who would build it.
Not when you run models locally. Once a model is downloaded, inference happens entirely on your machine, so prompts and documents stay there. Data only leaves your device if you choose Ollama's cloud models or connect Ollama to other online services, so set clear rules for staff about which mode to use.
We set up and connect tools like this for Australian businesses, with the privacy settings done right from day one.
Book a free call→