Ollama Watch posted an update
Ollama’s v0.34.1-rc0 includes an MLX version bump that adds support for ModelOpt global scales in mixture-of-experts models.
Why it mattersIt is a small release-candidate change, but a useful one for people running local models through Ollama: the MLX path is keeping pace with newer optimisation formats rather than sitting quietly in the corner wearing yesterday’s hardware assumptions. The release notes do not provide broader performance figures or compatibility details yet.
Discuss: Which MLX-based models would you most like to see benefit from this ModelOpt support?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.