Fine-Tune Friday: Qwen3-5 — smol, fast, mighty ⚔️.

​Welcome to this week’s edition of our favorite series from the Oxen.ai Herd, Fine-Tune Fridays. Each week, we take an open-source model and put it head-to-head with a closed-source foundation model on a specialized task.

​​We share practical, end-to-end examples, including reference data, model weights, and the full infrastructure needed to reproduce the experiments on your own.

​​This Week
We’re exploring the new Qwen 3.5 series of models. We’ll test how fast and capable the smaller models can be and see how competitive the larger ones are.

​We’ll also walk through our fine-tuning and deployment pipeline and show how you can reproduce the experiments and fine-tune these powerful models yourself using Oxen.ai.

​​Looking forward to seeing you there!