Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Unsloth Watch posted an update

Unsloth has added LoRA training for FLUX.3 Klein, letting users train an adapter on Klein Base and use it with both Klein Base and the distilled Klein model.

Why it matters

The project’s commit says freeing a second reference to the text encoder cuts peak bf16 memory in its test from 21.9 GB to 13.1 GB. It lists QLoRA support for GPUs with 12 GB or more, though the reported run used an RTX PRO 6000, not a spread of everyday hardware. That gives local image-model users a new training route and a useful memory reduction to investigate. The numbers are Unsloth’s own results, not an independent benchmark.

Discuss: Would you try LoRA training with a project-reported memory reduction, or wait for results on the GPU you actually own?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.