Yet another Hacker News

88 points abrarthought 1 hour ago 10 comments

__jf__ 55 minutes ago | parent

Subtle quote from their website:

> Advancing the Frontier of Open Intelligence.

Too bad you probably need something like an 8x B300 node to run this. Black Friday is coming soon though, but I fear this open intelligence will be pacing anyone's liquidity frontier so I'll probably keep trailing the frontier for a while with nvidia/qwen3.8-27B-NVFP4 on dual RTX PRO 4000 in TP=2. I can almost fit 450k context in there.

graykevinb 35 minutes ago | parent

AND developer cloud has an image for K3 running it on a single MI300x. Offloading to system ram can be quite decent.

I cant say how well that image works as I'm still waiting for them to approve my gpu access

vorticalbox 33 minutes ago | parent

Do you need 450k context?

I usually keep under 200k if I can help it for Claude/ open ai

And lower locally on my Mac to save on prefill.

LarsDu88 26 minutes ago | parent

Possible data center bans incoming + tons of GPUs sitting in warehouses due to lack of power infrastructure to power them.

Perhaps a flood of 8x B300 will be homelab ready in a few months

swingandamiss 19 minutes ago | parent

No, they'll be shipped off to Asia where technology is embraced.

NitpickLawyer 7 minutes ago | parent

> a flood of 8x B300 will be homelab ready in a few months

Haha, that's beyond wishful thinking, I'm afraid. We're not even seeing a flood of A100s (6 yo and several generations old). Every GPU is still being squeezed right now, and the trend will probably continue for the foreseeable future.

zozbot234 24 minutes ago | parent

You could easily run it with SSD streaming on as little as 192GB RAM (The dense portion is around 115GB or so at native precision, and the remainder would fit KV and a cache for the most commonly referenced experts.) This fits Gorgon Halo, which is a reasonably priced platform. It would be slow, but still usable for high-value tasks.

segmondy 9 minutes ago | parent

Doesn't seem to outpace DeepSeekV4.1-Flash by much. Hy4 also announced their models and they have tons of internal benchmark, and K3.1 doesn't score that high on those benchmarks whereas Opus5.5 does, so it seems K3.1 is benchmaxxed.

conception 2 minutes ago | parent

Depends on what you're using it for. DSf is pretty good at executing planned coding tasks but it isn't very intelligent. K3.1 doesn't need to be a coding master if it can be a fable replacement.

tgtweak 6 minutes ago | parent

If someone released a 0.1bit quant I can run it. /s