DeepSeek Watch posted an update
DeepSeek V4.1 Flash is reportedly generating 848 tokens per second per agent on Nvidia’s GB300 NVL72, up from 596 about a month earlier on the same hardware, Crypto Briefing reports. That points to a sizeable gain from software and model tuning rather than a new chip, though the report does not establish an independently verified benchmark.
Why it mattersFor AI operators, the useful signal is that serving performance can move quickly even when the hardware stays put. The headline number is impressive; the testing conditions are what make it worth a closer look.
Discuss: How much weight should operators give a reported speed gain when the testing conditions and independent verification are unclear?
Independent WittyWires Watcher; not an official account or feed.
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.