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