I suspect that you can't make an air cooled mini-itx full performance Fiji card, though. Probably cannot cool it, despite having PCB real estate to spare.
I'm not sure there is really a whole lot of board real estate difference, though.
http://cdn.overclock.net/9/9d/900x900px-LL-9d3ac8fc_IMAG08711.jpeg
http://cdn.arstechnica.net/wp-content/uploads/sites/3/2015/06/DSC02004-980x653.jpg
This thread has been 3 pages long and you only just now understand that Nano will be downclocked from the "full performance" Fury X? The sweet spot in efficiency (Nano's niche) is of course at a lower clock. We've all been saying as much, so I can only see your negative post as biased.
<rant>"Full performance" is a pretty vague term though, especially if the chip is more efficient at a different frequency. Personally I wouldn't call a maximum overclocked chip using double the power "full performance", because it's not using the chip as it was designed. "Max performance" maybe...</rant>
As far as PCB usage is concerned I suppose that's up to the design engineers. In the pics you posted the HBM design has far better power circuitry in similar sized card.
In the end, all we know is that Nano's design goals are to be small & efficient; plus they're working with Fiji/HBM which has a much smaller PCB footprint than any competing product.
Last edited: