Live data from Hacker News

Tinybox – A powerful computer for deep learning

tinygrad.org

31–40 of 372 posts

Re: Tinybox – A powerful computer for deep learning

#31
post #22

What’s the most effective ~$5k setup today? Interested in what people are actually running.

DGX Spark is a fantastic option at this price point. You get 128GB VRAM which is extremely difficult to get at this price point. Also it’s a fairly fast GPU. And stupidly fast networking - 200gbps or 400gbps mellanox if you find coin for another one.

Re: Tinybox – A powerful computer for deep learning

#32
There's no way the red v2 is doing anything with a 120b parameter model. I just finished building a dual a100 ai homelab (80gb vram combined with nvlink). Similar stats otherwise. 120b only fits with very heavy quantization, enough to make the model schizophrenic in my experience. And there's no room for kv, so you'll OOM around 4k of context.

I'm running a 70b model now that's okay, but it's still fairly tight. And I've got 16gb more vram then the red v2.

I'm also confused why this is 12U. My whole rig is 4u.

The green v2 has better GPUs. But for $65k, I'd expect a much better CPU and 256gb of RAM. It's not like a threadripper 7000 is going to break the bank.

I'm glad this exists but it's... honestly pretty perplexing

Re: Tinybox – A powerful computer for deep learning

#33

Finally, a computer that should be able to run Monster Hunter Wilds with decent performance. But let’s be real, 12k is kinda pushing it - what kind of people are gonna spend $65k or even $10M (lmao WTAF) on a boutique thing like this. I dont think these kinds of things go in datacenters (happy to be corrected) and they are way too expensive (and probably way too HOT) to just go in a home or even an office “closet”.

It’s not for people to buy. It’s for companies to buy. Compare to salary, and it’s cheap.

Re: Tinybox – A powerful computer for deep learning

#34
post #7

The exabox is interesting. I wonder who the customer is; after watching the Vera Rubin launch, I cannot imagine deciding I wanted to compete with NVIDIA for hyperscale business right now. Maybe it’s aiming at a value-conscious buyer? Maybe it’s a sensible buy for a (relatively) cash-strapped ML startup; actually I just checked prices, and it looks like Vera Rubin costs half for a similar amount of GPU RAM. I’m certai…

> The exabox is interesting. Can it run Crysis?

Probably, the rdna5 can do graphics. But it would be a huge waste, since you could probably only use one of the 720 GPUs

Re: Tinybox – A powerful computer for deep learning

#35

My interest in anything associated with geohot took a colossal nose dive today after seeing this post against democracy, quoting frelling M*ncius M*ldbug: Democracy is a Liability. https://news.ycombinator.com/item?id=47469543 https://geohot.github.io//blog/jekyll/update/2026/03/21/demo... Theres a lot there that makes sense & I think needs to be considered. But a lot just seems to be out of the blue, included withou…

For those unaware, Mencius Moldbug is the pen name of Curtis Yarvin, thought leader for the Silicon Valley branch of right-wing technofascist weirdos which includes Peter Thiel and apparently half of a16z.

Re: Tinybox – A powerful computer for deep learning

#36
post #22

What’s the most effective ~$5k setup today? Interested in what people are actually running.

Depends. If token speed isn't a big deal, then I think strix halo boxes are the meta right now, or Mac studios. If you need speed, I think most people wind up with something like a gaming PC with a couple 3090 or 4090s in it. Depending on the kinds of models you run (sparse moe or other), one or the other may work better.

Re: Tinybox – A powerful computer for deep learning

#37
post #31
post #22

What’s the most effective ~$5k setup today? Interested in what people are actually running.

DGX Spark is a fantastic option at this price point. You get 128GB VRAM which is extremely difficult to get at this price point. Also it’s a fairly fast GPU. And stupidly fast networking - 200gbps or 400gbps mellanox if you find coin for another one.

Internet seems to think the SW support for those is bad, and that strix halo boxes are better ROI.

Re: Tinybox – A powerful computer for deep learning

#38

My interest in anything associated with geohot took a colossal nose dive today after seeing this post against democracy, quoting frelling M*ncius M*ldbug: Democracy is a Liability. https://news.ycombinator.com/item?id=47469543 https://geohot.github.io//blog/jekyll/update/2026/03/21/demo... Theres a lot there that makes sense & I think needs to be considered. But a lot just seems to be out of the blue, included withou…

Geohot has always been an arrogant cunt who thinks he's better than everyone else. That blog post is totally on brand.

Re: Tinybox – A powerful computer for deep learning

#39
post #22

What’s the most effective ~$5k setup today? Interested in what people are actually running.

Sadly $5k is sort of a no-man's land between "can run decent small models" and "can run SOTA local models" ($10k and above). It's basically the difference between the 128GB and 512GB Mac Studio (at least, back when it was still available).

Re: Tinybox – A powerful computer for deep learning

#40

There's no way the red v2 is doing anything with a 120b parameter model. I just finished building a dual a100 ai homelab (80gb vram combined with nvlink). Similar stats otherwise. 120b only fits with very heavy quantization, enough to make the model schizophrenic in my experience. And there's no room for kv, so you'll OOM around 4k of context. I'm running a 70b model now that's okay, but it's still fairly tight. And…

It will work fine but it’s not necessarily insane performance. I can run a q4 of gpt-oss-120b on my Epyc Milan box that has similar specs and get something like 30-50 Tok/sec by splitting it across RAM and GPU.

The thing that’s less useful is the 64G VRAM/128G System RAM config, even the large MoE models only need 20B for the router, the rest of the VRAM is essentially wasted (Mixing experts between VRAM and/System RAM has basically no performance benefit).

Post reply on HN