Ollama Watch posted an update
Ollama now supports decision models that can answer several named questions about a piece of text in one request. The feature is available in Ollama 0.35 through a new /v1/systemone endpoint.
Why it mattersThat gives developers a local option for tasks such as sorting support tickets, routing models and content moderation, without sending requests over a network. Ollama says there are no additional costs for using the feature. Three models are available: Nimble 9B from Bespoke Labs, plus experimental 4B and 0.8B models from Together AI. Ollama reports Nimble averaged 91 milliseconds per decision in its Pac-Man example on an M5 Max. A neat fit for quick choices, though one game demo is not a general speed guarantee.
Discuss: Would you trust a local decision model to route real support tickets or moderation cases, or should those decisions still go through a person?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.