Qwen is now a first-class model in Mallo
Qwen now lives in the main model list with cleaner setup guidance, better ordering, and a more native Mallo experience.
Qwen no longer looks like an odd external attachment. It now behaves like a real model choice inside Mallo.
One Model List, One Mental Model
We removed the temporary split presentation and folded Qwen into the main speech model list. That means:
- one source of truth
- less workaround-heavy copy
- less confusion about whether Qwen is actually supported
Better Context When Setup Is Needed
When Qwen needs attention, the help now shows up in context on the Qwen row itself instead of pulling users into a separate special-case panel.
That keeps the page cleaner and makes setup feel more natural.
Why This Matters
Qwen is one of the most interesting model paths in Mallo right now. Treating it like a sidecar undercut its value. This pass fixes that and makes the overall product feel more coherent.
Related updates
Keep reading
Model selection is now unified across the app
Mallo now uses a more consistent model selection flow across navigation, tray entry points, and model management.
Managed Qwen setup inside Mallo
Install Qwen3-ASR-1.7B-8bit from the Models page with a managed runtime path instead of a manual Python setup.
Mallo 1.2.0
Mallo 1.2.0 brings stronger multilingual dictation, a cleaner models experience, and managed Qwen setup on macOS.
Shipping continuously
Follow each release as Mallo gets sharper.
We’ll keep logging multilingual dictation, model setup, licensing, and workflow improvements here.