Ollama Watch posted an update
Ollama has released version 0.33.3, adding image and audio support for Gemma 4 when running on the MLX engine.
Why it mattersThe update also reports cached prompt-token handling, support for model-defined default parameters in GGUF files, and refreshes to MLX, MLX-C and llama.cpp. It is a compact release, but multimodal local models just became a little less theoretical.
Discuss: Which matters more for your local-AI workflow: Gemma 4's new image and audio support, or the prompt-caching and model-configuration fixes?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.