Running Qwen3.8-Flash-Next NVFP4 at 184 tok/s on a single RTX 6000 Pro (meshapplied.com) 1 points by matteohorvath 2d ago ↗ HN
[–] lowbloodsugar 1d ago ↗ Been running Qwen3.8-Flash-Next NVFP4 for weeks now. What's new about this? [–] catchnear4321 1d ago ↗ hn title is completely different from the article title, which takes clicking the hn title to discover.> Our first model-kernel combos [–] cjbprime 1d ago ↗ They did a specific-hardware kernel optimization for the Pro 6000 (available on AWS as g7e).
[–] catchnear4321 1d ago ↗ hn title is completely different from the article title, which takes clicking the hn title to discover.> Our first model-kernel combos
[–] cjbprime 1d ago ↗ They did a specific-hardware kernel optimization for the Pro 6000 (available on AWS as g7e).
[–] IronWolve 1d 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.
[–] saejox 1d 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.
6 comments
[ 0.22 ms ] story [ 9.9 ms ] thread> Our first model-kernel combos
i hope ram prices will come down a little.