Design & Reuse

Tenstorrent QuietBox tested: A high-performance RISC-V AI workstation trapped in a software blackhole

$12K machine promises performance that can scale to 32 chip servers and beyond but immature stack makes harnessing compute challenging

Nov. 27, 2025 – 

hands on Tenstorrent probably isn't the first name that springs to mind when it comes to AI infrastructure. But unlike the litany of AI chip startups vying for VC funding and a slice of Nvidia's pie, Tenstorrent's chips actually exist outside the lab.

If you're feeling a little non-conformist and want to color outside the lines, Tenstorrent parts and systems are readily available to anyone that wants them. In fact, you may be surprised to discover the company has already shipped three generations of its RISC-V-based accelerators in an effort to build momentum within the open-source community.

Their philosophy is to deliver a reasonably performant accelerator that can scale efficiently from a single card to a 32-chip system and beyond, at a fraction of the cost of competing AMD or Nvidia GPU boxes. 

El Reg recently had the privilege of going hands-on with one of the startup's most powerful systems to date, an $11,999 liquid-cooled AI workstation called the Blackhole QuietBox. The 80-pound (36 kg) machine is essentially a cut-down version of the chip startup's upcoming Blackhole Galaxy servers, which are expected next year. It's designed to serve as a development platform to learn the architecture, port over existing code bases, and optimize model kernels before pushing them to a production system.

 

And, because the machine uses the same chips, memory, and interconnects that you'll find in Tenstorrent's Galaxy servers, that work should theoretically scale seamlessly to the full system — something that isn't generally true of most AI workstations available today. Sure, you could toss four RTX 5000 Adas or Radeon Pro AI R9700s into a similarly equipped workstation and find yourself in the same ballpark as the QuietBox, but performance characteristics of those systems will be wildly different than the GB200 racks or MI350 boxes your code would eventually end up running on.

This is one of the reasons why Nvidia has periodically released systems like the DGX Station, which cram the same CPUs and GPUs found in its datacenter class products into a more office-friendly chassis. Having said that, we fully expect Nvidia's next-gen Blackwell Ultra-based DGX Station to cost several times what Tenstorrent is asking for the QuietBox.

Click here to read more...