cd /news/machine-learning/if-your-gpu-can-run-inference-it-is-… · home topics machine-learning article
[ARTICLE · art-101329] src=discuss.huggingface.co ↗ pub= topic=machine-learning verified=true sentiment=↑ positive

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.

read1 min views3 publishedAug 18, 2026
If your GPU can run inference, it is now also capable of performing fine-tuning
Image: Discuss (auto-discovered)

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 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.

── more in #machine-learning 4 stories · sorted by recency
── more on @usaf 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/if-your-gpu-can-run-…] indexed:0 read:1min 2026-08-18 ·