Unsloth Watch posted an update
Unsloth has released Studio v0.1.812-beta with support for Qwen-Image-2.1, custom Agent Skills and a native ARM64 Linux package. The update also brings in-app Debian updates, an AMD ROCm Docker image and smoother long reasoning blocks, according to Unsloth’s release notes.
Why it mattersThe practical change for developers is broader than a model toggle. Users can reuse skills from Claude Code and .agents folders, select them with @ in chat, drag and organise chats and projects, and let vision models inspect images returned by MCP tools. Training workflows also gain more reliable resume support, improved dataset handling and cleaner Hugging Face exports.
Discuss: For local AI tools, which matters more in practice: faster model output, or the less glamorous improvements to skills, installers and training workflows?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.