Qwen3.5-2B

Headlines · 2

1. 7d
   Unsloth trains a decision model on Qwen3.5-2B in about 2 minutes on one DGX Spark

   Unsloth shared an Ivan Fioravanti demo showing a "decision model" trained in roughly two minutes on a single NVIDIA DGX Spark using Unsloth, with Qwen3.5-2B as the base model. The post points to Unsloth's documentation page on training your own decision model with Unsloth. The source gives no details on the model's intended use, evaluation results, or training data.

   UnslothAI (X) · 🔥 0
2. Oct 8
   Hugging Face's ML Intern builds six small models in days on a tiny budget

   In a Hugging Face blog post, author yvrjsharma describes using the ML Intern agent inside HuggingChat to build six models in a couple of days, including distilling Qwen-Image 2.1's 9B prompt rewriter into a 0.8B 'Pocket' version that runs on CPU (99.7% valid output, about a quarter of the teacher's tokens) and fine-tuning Qwen3.5-2B for citrus-disease diagnosis, which rose from 14.9% to 52.8% accuracy on 335 test images. The agent plans the work, requests a budget before spending, runs a smoke test, then trains, evaluates and publishes to the Hub; the author puts the first project's total compute at about USD 16. The post also shares prompting advice, such as asking for a pre-training baseline and capping total spend.

   Hugging Face · 🔥 0

Experience and discussion from the community

Share my Qwen3.5-2B experienceAsk about Qwen3.5-2B