Ollama adds a local brick for simple decisions
Instead of a large agent for each step, a small typed decision can route a request or rank a ticket. It is a concrete track to reduce calls to heavier models.
Available from 0.35
Facts, analysis and limits
Verified facts
- Ollama 0.35 adds the decision models and the /v1/systemone endpoint: a state and named questions produce typed answers.
- Use cases cited include triage, routing and moderation; Nimble 9B, Tev1 4B and Tev1 0.8B are offered for local execution.
- The 91 ms per decision announced for Nimble comes from an example Pac-Man on M5 Max, not from a latency guarantee on your VPS.
What changes
For Syndiko, test request triage on an annotated dataset before taking any action. Include an unknown class and a confidence threshold; never trigger a sensitive action from the score alone.
Practical implication
Build a read-only classification prototype; no model was installed in this pilot.
Availability
Ollama 0.35+; material requirements, memory and latency to be measured on the target machine.
Limits and uncertainty
Local does not mean without cost: equipment, maintenance and quality of ranking remain to be evaluated.
29 Sept. · e-mail 30