unslothai/unsloth v0.1.906-beta: Browser Use + Qwen-Image-2.1-Turbo
Models can now use the browser in Unsloth.
ProofCode ↗
Key points
- Qwen-Image-2.1-Turbo is here too, making images in just 8 steps.
- Also included: text-diffusion LLM training, faster MoE GGUFs and speculative decoding on Mac.
- Browser use. Models can open pages, click, type and scroll in the Unsloth Browser
- Run Qwen-Image-2.1-Turbo, the official 8-step version of Qwen-Image-2.1, from the Images page, with a 4.2 GB Q4 GGUF.
Sources (1)
- [1]unslothai/unsloth v0.1.906-beta: Browser Use + Qwen-Image-2.1-TurboGitHub: unslothai/unsloth · Oct 12, 02:17 PM
Models can now use the browser in Unsloth.
Qwen-Image-2.1-Turbo is here too, making images in just 8 steps.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 11, 2026MCP - Qwen2.1 Turbo + Kandinsky Lite Video Gen on 8GB VRAM
- Oct 10, 2026Krea2 Turbo Distill 2 step LoRA - FINAL checkpoint released (chk51195)
- Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
- Oct 9, 2026Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
- Oct 8, 2026huggingface/trl v1.15.0
- Oct 8, 2026unslothai/unsloth v0.1.905-beta: Sandboxing is here!