Transformers

Unsloth now supports running Qwen3.8 models locally with reduced RAM requirements and offers significant performance improvements, including faster inference for GGUFs and MiniMax-H3. New features enhance chat capabilities, tool integration, and hardware compatibility.

This release focuses heavily on stability, VRAM reduction (10-25% less), and broad model compatibility, including full fixes for Gemma 3N Vision and support for new models like Devstral 1.1 and MedGemma.

This maintenance release focuses on stability and bug fixes across various components, including UI responsiveness, model loading stability (especially with FP8 and Flux.2), and CI/CD pipeline improvements. Future major features like video generation are noted for version 6.14.0.

This maintenance release focuses on stability and bug fixes across the UI, model loading, and CI/CD pipelines. Key updates include support for PEFT named-adapter LoRAs and dependency upgrades for React, ROCm, and Transformers.