Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AMD Ryzen AI Halo – $4k AI Dev Kit

lttlabs.com

Post reply on HN
Print view View original

211–220 of 274 posts

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#211

Post by gessha »

prima-facie wrote: post #190
Tenoke wrote: post #51

I really want a 128gb+ machine but it's brutal to be at only 256 GB/s for $4k (especially with the drawbacks of both ARM and AMD). I fear that by the time the RTX Spark comes out it'd have to be $6k, and by the time a 128gb or more machine with 700+ GB/s comes out it'd be at $10k, way out of most consumers' hands. Edit: capitalized gb/s to GB/s.

At the moment, for around $4000-5000 you can either have speed (a GPU + 32GB VRAM), or you can have capacity - a DGX Spark/Halo, but not both. I think once someone comes up with a machine which has both it will easily sell for $10000 and people will be queueing to buy it.

That’s about the price of a workstation-class Nvidia GPU nowadays and if you splurge double, you can get a PCIe version of a data center card.

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#212

Post by jauntywundrkind »

wmf wrote: post #66
jauntywundrkind wrote: post #54

Earlier quoted context omitted.

From the replies, > A shame, really, as the Ryzen 7640U, 7840U, 7840HS, and 7940HS all support 256GB of RAM. To be fair, those platforms support dual dimms per channel, which Strix Halo would not, at least not at it's high speeds. But reciprocally Gorgon Halo 400 just launched and it supports... 192GB. And is the exact same APU. Memory chips did finally have their first big doubling per chip semi recently (available…

I assume they validated certain DRAM chips when the 395 first came out and they're just not going to validate any more. So newer DRAM is validated for the 495. We can't compare DDR5 and LPDDR5 since they are completely different; if 256 GB DDR5 is possible that doesn't mean anything.

But 192GB lpddr5x on Goron Halo 495 does strongly strongly suggest 256GB would be too. It took some big work to go from 32GB to 64GB dimms, was a long long long time coming. 48GB came latter.

Its very unlikely that with 192GB Gorgon Halo that anything really blocks 256GB Gorgon Halo, or Strix Halo. Higher than 32GB chips are possible and exist.

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#213

Post by teravor »

lhl wrote: post #13

The one thing that's new/worth pointing out are the https://developer.amd.com/playbooks/ ( https://github.com/amd/playbooks ) - this is AMD's answer to Nvidia's playbooks ( https://build.nvidia.com/spark / https://github.com/NVIDIA/dgx-spark-playbooks ) - I think it's great that they're actually taking this more seriously. Hardware is the exact same as what used to be available for $2K last year (and is still $1K che…

it's worth noting that AMD's software is universally weak and not worth any degree of reliance. and it's not just ROCm, every few months they merge a serious regression into amdgpu and sometimes even backport it into stable. they are amateurs.

just a few weeks ago they backported a kernel oops amdgpu null dereference into stable, it's still not fixed.

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#214

Post by hypercube33 »

Tenoke wrote: post #63
dabinat wrote: post #62

Earlier quoted context omitted.

A Mac Studio is a much better buy in terms of memory bandwidth, but impossible to buy in a 128 GB configuration. Honestly there aren’t great options right now and it’s probably better to wait for the market to be less insane.

I looked for one and it's impossible to find, let alone at a reasonable price + it does suffer from being harder to train/use less common models and workflows (e.g. arbitrary comfyui ones). Spark at least doesnt have that drawback, while AMD has both drawbacks. Waiting for the market to be less insane is somewhat akin to waiting for the s&p500 to drop a decent amount so you can buy in.

Asus rog 13 128gb is still sub $3k last I checked and ticks the boxes. If you get tired of AI it's a kick ass tablet except the weight and can run AAA games for now decently enough.

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#215

Post by verdverm »

Catloafdev wrote: post #23

These devices were great when they were cheaper than the DGX Spark. But when they cost the same price (unless the Spark has shot up too), there's no reason to buy this over a Spark. The Spark is literally a faster version of this, with better software support. Edit: And I say that as an owner of a Ryzen AI Max 395 device.

Spark has also gone up in price, my second cost me $500 more than my first a couple months earlier (both this spring)

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#216

Post by jaxytee »

codedokode wrote: post #71
vlian2088 wrote: post #25

Earlier quoted context omitted.

it's 2026.07 and 128 GB of VRAM costs a firstborn.

Please note that 8 x 16 Gb DDR4 modules cost $480, and have a bandwidth of 200 Gb/s, the only problem you need 8 DRAM controllers.

Running large MOE models won't saturate the EPYC memory.

You'll never see that 200 Gb/s running inference.

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#217

Post by icedchai »

teravor wrote: post #213
lhl wrote: post #13

The one thing that's new/worth pointing out are the https://developer.amd.com/playbooks/ ( https://github.com/amd/playbooks ) - this is AMD's answer to Nvidia's playbooks ( https://build.nvidia.com/spark / https://github.com/NVIDIA/dgx-spark-playbooks ) - I think it's great that they're actually taking this more seriously. Hardware is the exact same as what used to be available for $2K last year (and is still $1K che…

it's worth noting that AMD's software is universally weak and not worth any degree of reliance. and it's not just ROCm, every few months they merge a serious regression into amdgpu and sometimes even backport it into stable. they are amateurs. just a few weeks ago they backported a kernel oops amdgpu null dereference into stable, it's still not fixed.

The "ROCm" situation with Strix Halo was pretty bad for a while. I think it finally stabilized late last year. You needed the right combo of ROCm, Linux kernel, and kernel firmware for it to work reliably.

Whenever I rebuild llama.cpp, I wind up using the Vulkan build anyway.

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#218

Post by kristianp »

__rito__ wrote: post #104

I was in Gray Scott School for HPC last week, and even in scientific usage, CPU-only cases, AMD is still a pain point. Many tools and libraries don't have first class AMD support or any support at all. It loses to Intel in CPU, and NVIDIA in GPU, in case of scientific libraries and HPC-worthy libs, tools. I think people who want an "AI Dev Kit" will lean towards Intel + NVIDIA setup. I am not a fan of Intel, but thei…

> It loses to Intel in CPU

Not really, their CPU market share has dropped in the last decade.

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#219

Post by cthalupa »

grubbs wrote: post #136
frugalmail wrote: post #93

Earlier quoted context omitted.

I'm looking at Amazon and I see $4k GB10 devices right now (not an affiliate link) https://www.amazon.com/ASUS-Supercomputer-Superchip-Supports...

Yea I mentioned the FE version which is 4TB NVME. The one you linked is 1TB NVME.

I snagged my two 4tb acer variants for under 4k each. CDW still has them listed for close to what I paid.

Re: AMD Ryzen AI Halo – $4k AI Dev Kit

#220

Post by cthalupa »

codedokode wrote: post #122
icedchai wrote: post #86

Earlier quoted context omitted.

In the alternate reality where this happened, wouldn't the price of DDR4 still be sky high? We'll ignore any costs for CPU, chip set, and motherboard redesign. You're just pushing the demand somewhere else.

> any costs for CPU, chip set, and motherboard redesign. Yes they spent those costs to switch from DDR4 to over-priced DDR5 and I suggested the cost could be spent on adding more DDR4 channels instead.

The problem is if DDR4 was viable here it would also be absurdly expensive. There’s no world in which we survive this demand without a corresponding increase in supply. It’s not like there are zettabytes of spare cheap DDR4 sitting around.
Post reply on HN