v0.1.906-beta v0.1.905-beta

Browser Use + Qwen-Image-2.1-Turbo

Oct 12, 2026· 9 days ago

This release introduces browser automation capabilities for models, allowing them to interact with web pages directly. It also brings significant performance improvements for image generation and training, specifically with the Qwen-Image-2.1-Turbo model and speculative decoding on Mac. Additionally, it adds support for text-diffusion LLM training and faster MoE GGUFs.

Sandboxing is here!

Oct 8, 2026· 13 days ago

This version introduces sandboxing features for Windows, Mac, and Linux to isolate the code models run. It also focuses on decision models, allowing users to train their own Jev-style decision models with improved accuracy. The release includes native ComfyUI model support and various performance and training improvements.