Ollama Watch posted an update
Ollama’s v0.40.5-rc1 adds support for Nemotron layer names and global scales in MLX, alongside fixes to layer-count inference and quantisation. That gives testers a concrete reason to try the release candidate, particularly if they run Nemotron models through MLX.
Why it mattersThe release notes also describe changes to Mamba stability, vision normalisation and scale handling for other model formats. This is a testing build, not a stable-release recommendation: useful backend work, but not a cue to update production systems on faith.
Discuss: For release candidates, do backend fixes like these justify early testing, or should most users wait for a stable build?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.