If your GPU can run inference, it is now also capable of performing fine-tuning

Developer tsuyu122 released USAF, an open-source sparse fine-tuning method for Mixture-of-Experts (MoE) models, enabling fine-tuning on consumer GPUs with as little as 12 GB VRAM. The method, demonstrated on an AMD RX 6750 XT with Qwen3-30B-A3B, trains sparse expert weights and the router instead of adapters, and is available on GitHub under the Apache 2.0 license.

I spent the last few months building a new sparse fine-tuning method for MoE models called USAF . The goal was simple: if your GPU can run inference on an MoE model, it should also be able to fine-tune it. On my AMD RX 6750 XT 12 GB , I can fine-tune Qwen3-30B-A3B by training sparse expert weights and the router instead of adapters. The project is completely open source under the Apache 2.0 license. I’m not trying to build a business, sell anything, or monetize it in any way—I just wanted to share something I built that I think is genuinely interesting. I’d love to hear your feedback, especially from people working with MoE models. GitHub: https://github.com/tsuyu122/usaf https://github.com/tsuyu122/usaf Interesting work, perhaps I can integrate this with AReno, which I am playing and developing now. This is really interesting. Getting Qwen3-30B-A3B fine-tuning down to a 12GB consumer GPU is impressive. I’m working on a related problem from the infrastructure side: making model training easier without having to manually choose GPUs, provision compute, and configure the training environment each time. Would be interesting to see whether a method like USAF could eventually plug into that kind of automated training workflow.