Hacker News new | ask | show | jobs
by nightski 26 days ago
I recently bought a few sparks from Micro Center for the exact same price and it comes with ConnectX-7 200Gbps inter-connectivity. Not sure how AMD feels it can charge exactly the same for less.
1 comments

it's 2026.07 and 128 GB of VRAM costs a firstborn.
The spark also has 128GB VRAM (same type) and by recently I mean I bought them last week for $3999 each.
yeah, so $500 spread https://www.microcenter.com/product/699008/nvidia-dgx-spark is what the current price appears to be.

The differences are basically, sparks require ARM and sparks allow interconnects; so if you do have dreams of electric sheep to chain them together, you're not gonna get the AMD halo units.

But if you just want to putz around with a dev machine and do other things, not sure you'd want a spark.

They had it on sale last week for $3999, it will likely happen again. Also if you are willing to buy ASUS/Acer/MSI you can get them cheaper, in the same range as well. Those units are identical (mainboard/ram/chipset/connectivity), they only tend to differ in SSD being offered.
The more beneficial difference between DGX and OEM Spark is in cooling. DGX has had cooling issue based on user reports.
Only Asus from what I have seen. Acer/Dell units seem to run cooler than the Nvidia unit, by a noticeable margin. That said I bought the OEM units for the Gen 5 4TB SSD and the fact that it was on sale.
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.
> the only problem you need 8 DRAM controllers.

Which is a huge problem? Even using 2x memory controllers in typical consumer motherboard can make system very unstable.

Why is that so?
Running large MOE models won't saturate the EPYC memory.

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

Because it'll bottleneck at the CPU? Or because 200 bB/s is overkill when running a model (that fits in memory)?