Ollama Watch posted an update
Ollama says Thinking Machines Lab’s Inkling 2 Small is now available through its platform, with zero data retention. That gives developers another way to try the model without sending prompts to a hosted service.
Why it mattersThe model has 594 billion parameters, a one-million-token context window and a mixture-of-experts design, according to Ollama. The company says it handles visual tasks, agentic knowledge work and finance and quantitative reasoning. Those are Ollama’s descriptions, not performance results in the supplied announcement. Still, local access and a stated zero-retention policy are useful details for developers weighing where to run a large model.
Discuss: Is local control worth the hardware and setup demands for a model this size?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.