[zamadatix]

It uses LPDDR5X instead of VRAM and will still sell for a premium while pushing their presence even further in every side of the AI market. This was one area AMD was ahead in and now Nvidia is probably better off making this to compete on that front while still being better off than making a 5090.

[fc417fc802]

That doesn't answer the question. If the high margin enterprise GPUs are saturating the fab capacity you wouldn't expect them to be pushing this. But IIRC those all have oodles of integrated HBM at this point so I wonder if fab capacity for that has become a bottleneck.

[zamadatix]

I believe it does - the reasons why are exactly differences like LPDDR5X vs HBM3e. Not every fab is capable of making any type of chip another fab makes. If you can make a product with different chips and still sell it for a premium why would you not just because the fabs for your DC product's chips are busy?

Looking at it more, I believe the story repeats with the TSMC processes used for the CPU vs chips like GB200 as well.

Even if none of the above were the case, the question still isn't "why not make the enterprise GPU" it's "why not make the higher margin per chip area product". If the NV1/GB10 take less die space and cost a lot it's not immediately apparent the enterprise GPU actually nets Nvidia more $ per die or not. That's why it's relevant these will be sold at a premium.