Ollama
One command to run a serious model on your own computer

Open source✓ VerifiedSelf-hostable
Open Ollama → Back to the index

Our take

`ollama run` and you have a capable model on your machine, offline, with no per-token cost. If you run anything at volume — tagging, drafting, summarising — this is the difference between a hobby and a margin.

Watch out

Model quality scales with the RAM you have. On 8 GB you get toys; the useful ones want 16–32 GB+.

The free tier, in detail

What you get freeFree and open source (MIT); models download once and run offline forever
Where the limit sitsNo limits beyond your own hardware — bigger models want serious RAM
Credit card to startNo
Pricing typeOpen source
Last checked2026-07-30 · source
Run it yourselfYes — MIT · repo
Platformswindows, mac, linux, api
CategorySelf-hosted / local · Code & dev · Chat & assistants

Similar tools we've checked

Get told when this free tier changes

We recheck every entry. Subscribers hear first when a free tier quietly shrinks.

© Edge the AI · Independent & not sponsored · Some links are affiliate links — they never change a verdict.
Free tiers change without notice. Every entry shows the date we last checked it. Found something wrong? hello@edgetheai.com · Privacy