Got my little Strix Halo workstation for early Christmas

So I treated myself to one of these

measures 6x9x3.5 or so, weighs the same as a brick more or less, has 128GB of RAM, 96 of which I’ve assigned as video memory. I can run sizeable large language models at home, with… leisurely speed, let’s say, but it’ll run things you can’t run without setting up several Nvidia GPUs in a single machine or some kind of cluster. And it’s dead silent most of the time, when you’re not asking for heavy work. Lovely little box.

I’m learning, though, esp. under Windows, how much work lies ahead to make common AI tooling comfortably compatible with ROCm compared to stuff just working with NVDA. I’m making good progress – got Docker, ollama, and some chatbots up, a nice UI for chatting and image generation, and a workflow engine that can eventually support Agentic AI… Trying to understand how, in reality, all these pieces fit together in the real world by building myself a modest but meaningfully capable environment of my own. So… many… moving parts, and then the fact that some core things don’t work under ROCm without A LOT of unsupported hoop-jumping and hacks. Still, gratifying to see progress.

I can only assume that a) on Linux a lot of things work better (don’t ask me about Docker for Windows not exposing your graphics hardware to anything running in Docker) and b) when Lisa Su sells the AI hardware to hyperscalers and large enterprises, they do A LOT of handholding.

On a tangentially related note: it scares me that there are Strix Halo handheld consoles with 128GB of RAM, and the same ability to assign massive memory to VRAM and run the kind of stack I have now. Who needs THAT for a game?

3 Likes

Nice! You got this for work or play? Not too bad price wise either, with the current steep discount HP has presently. A mere $3700 for:

  • Windows 11 Pro

  • AMD Ryzen™ AI Max+ PRO 395 (up to 5.1 GHz max boost clock, 64 MB L3 cache, 16 cores, 32 threads)

  • 128 GB memory; 4 TB SSD storage

  • AMD Radeon™ 8060S Graphics

it’s for a mix of work and play but primarily for me to fool around with agentic AI technologies at home and learn how this stuff really works because as a product manager, the whole industry is reorienting around these technologies and I don’t want to run up credit card bills with 10 different services and try to figure out how to lash together stuff from different third parties in the cloud just to make hello world work.

if I’m going to be employable I need to understand this stuff, but right now it’s not revenue generating in any way And I don’t expect to directly make money off this machine.

one other thing: I actually feel pretty amazing about having bought it before Christmas. I don’t think I put the price I paid in my previous post. I got the highest end spec except for only a 2 TB SSD instead of 4 TB, and I only paid about $2,400. And that includes 3 years of on-site service. there were and are a bunch of less well-known brands offering similar configurations for about $250 less. if HP IS now asking well over $3,000 for that, I did great. I think I ordered it on Cyber Monday, definitely somewhere in the Black Friday weekend thing. and I found a 10% off coupon code at the last minute that knocked it down from about $2,600.

1 Like