Inferencer v1.11.1 with Multimodal Inference

In version 1.11.1, we added full multimodal inference support, including image and audio models, along with model streaming support for Kimi K2.6, improved loop detection for code blocks, and a range of performance and stability improvements.

Multimodal Inference

We’ve added full multimodal inference support, allowing you to work with both image and audio models directly inside Inferencer. You can now switch between vision and language models within the same conversation, making it easier to move between different types of reasoning without losing context.

Media attachments are now saved with messages and cached locally, while audio previews and compatibility-aware attachment options make it easier to understand what has been included in a conversation. We’ve also added tool call support for multimodal conversations, prompt cache retention and regeneration options for vision messages, and improved model streaming controls with safer handling for vision models.

More Improvements

In this release, we’ve also:

• Added support for DeepSeek V4, MiMo V2.5, and LongCat Next
• Added model streaming support for Kimi K2.6
• Improved loop detection for code blocks
• Added new window and tab behaviour, including Command + T support
• Made Command + Shift + N start a new message
• Added remote generation progress to the Tasks view
• Added prompt processing notifications
• Improved handling of failed or cancelled multimodal messages
• Improved detection for MiniMax model files
• Fixed batching issues for Kimi K2.6
• Fixed dock icon and window focus issues
• Fixed WebView interaction and right-click issues
• More bug fixes and performance improvements

As always, if you have any features or suggestions you’re more than welcome to add them to our public roadmap.

Thanks again for your support, and as a reminder, all AI processing is done offline, directly on your devices. No telemetry, no background "update" checks.

P.S. If you find Inferencer useful, please consider leaving a review on the App Store. It would be much appreciated.