N
Hacker Next
new
past
show
ask
show
jobs
submit
login
▲
Running Qwen3.8-Flash-Next NVFP4 at 184 tok/s on a single RTX 6000 Pro
(
meshapplied.com
)
28 points by
matteohorvath
2 days ago
|
6 comments
add comment
IronWolve 2 days ago
[-]
Been running versions of this on my pc, if you have 64 gigs ram, you can run it on a 12+ gig cards easily.
aappleby 2 days ago
[-]
On "just" a RTX 6000 Pro? You mean one of those $16,000 gpus?
saejox 2 days ago
[-]
it is very hard to run 150k token context with these kind of setups. even if you do, all of us are used to running multiple agents at once.
i hope ram prices will come down a little.
lowbloodsugar 2 days ago
[-]
Been running Qwen3.8-Flash-Next NVFP4 for weeks now. What's new about this?
catchnear4321 2 days ago
[-]
hn title is completely different from the article title, which takes clicking the hn title to discover.
> Our first model-kernel combos
cjbprime 2 days ago
[-]
They did a specific-hardware kernel optimization for the Pro 6000 (available on AWS as g7e).
Rendered at 09:17:28 GMT+0000 (Coordinated Universal Time) with Vercel.
i hope ram prices will come down a little.
> Our first model-kernel combos