X · by Unsloth AI
Train your own decision model with Unsloth
Qwen3.5 0.8B from 20.7% to 74.3% accuracy, on 4GB of VRAM.
Unsloth AI
@UnslothAI
You can now train your own Decision model like Jev locally! We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM. Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo. We fine-tuned with a Clef head using Unsloth and LoRA (r=64) for one epoch, increasing downstream accuracy from 30–37% to 78%. GitHub: https://github.com/unslothai/unsloth Guide and Notebooks: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth
Oct 7, 2026 · 3.9K likesOpen on X
Unsloth published an open-source recipe to train a decision model like Jev on your own machine. It raised the aggregate accuracy of Qwen3.5 0.8B from 20.7% to 74.3% across three decision benchmarks, on 4GB of VRAM. The same repository turns other LLMs, such as Qwen3.8 and Gemma 4, into decision models.
Open the source
