Ollama prerelease exposes model thinking controls through its API
According to the Ollama release note, the api/show response now reports each model’s supported thinking controls and its default choice. Clients can therefore read this capability from the API instead of assuming it separately for each model.
According to the Ollama release note, the api/show response now reports each model’s supported thinking controls and its default choice. Clients can therefore read this capability from the API instead of assuming it separately for each model. github.com
The same prerelease adds MLX support for Nemotron H vision models on Apple Silicon. The release note lists this as a newly supported execution path and does not provide an independent performance result. github.com
The release note also changes the macOS app so windows closed by the user are not reopened when the app is activated again. It provides no additional technical detail for this change. github.com
This report is based on published technical documentation. GlobalFeed has not independently benchmarked the implementation.
