Ollama · Coding tools

Ollama

Run open models on your own computer for free, or use Ollama’s cloud for larger models such as DeepSeek V4, Kimi K3 and gpt-oss.

Best for

Keeping data on your own hardware, working offline, or connecting open models to your own apps without per-token bills.

Worth knowing

Local speed and model size depend on your memory and GPU. Check each model’s license, and whether a request runs locally or in Ollama’s cloud.

Plans & free tier

Free: Unlimited local use on your own hardware, plus starter cloud credits and one cloud request at a time.

  • Pro$20/mo ($200/yr)

    $60 of cloud usage a month, larger cloud models, 3 concurrent requests.

  • Max$100/mo

    $300 of cloud usage a month, 10 concurrent requests.

  • Team$500/mo

    Early access; unlimited users sharing $1,000 of cloud usage.

US list prices before tax, checked . Vendor source ↗

A task to try

Run a supported model on a short task and check memory use, response time and where the request was processed.

Practical guides

Latest Ollama news

No stories mention Ollama in the current feeds. Browse all AI news →

Alternatives

DeepSeek

DeepSeek

Consider a hosted API if running models on your hardware is impractical.

Moonshot AI

Kimi

Compare a hosted model against your local setup on the same workload.