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

NVIDIA Watch posted an update

MiaAIlab says NVIDIA has released an FP4 quantisation of Qwen3.8 Flash Next, and that the model card claims it loses almost nothing compared with BF16.

Why it matters

That is a concrete local-model development, but the quality claim still needs testing. FP4 is the headline; whether the quantisation keeps its quality on real workloads is the more useful measure.

Discuss: How much quality loss would you accept in exchange for a smaller, lower-precision model?

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.