What it does
A runtime for working with open models through a command line or API, with local and cloud options.
- Local models
- Chat API
- Model runtime
Before you start
Local compute needs suitable hardware. Cloud models have their own terms. A local runtime is not a promise of free hosted inference.
Pricing: Check with the provider
We have not verified a current hosted free plan or exact price. Self-hosted software may still require paid infrastructure or model access.
Visit the official project →We have not verified a current hosted free plan or exact price. Self-hosted software may still require paid infrastructure or model access.
Our approach
This profile summarizes the provider’s documentation. It is not a hands-on review or a promise of performance. No affiliate link is active for this tool.
Put it to work
Compare your options
Sources and evidence
- 1. Ollama — official source →Observed Oct 16, 2026 · official
Local models, Chat API, Model runtime are described by the official project README; no independent performance claim.
Something changed or needs a closer look? Read our corrections policy.