Comment by MrBuddyCasino
12 hours ago
As best as I can tell its something like the Apple M series SoC, but for Windows: CPU + GPU with unified memory.
It has 6,144 CUDA cores is similar to a RTX 4070 (5,888) but a lot less than a 4090 (16,384), but what it does have is support for FP4.
When they claim "1 Petaflop AI compute", thats what they mean. For comparison, a RTX 4090 has ~1.3 Petaflops of FP8 processing.
The second big deal is the NVLink-C2C interconnect, which provides up to 900 GB/s of bidirectional bandwidth between GPU and CPU. For comparison, the Apple M4 has 120 GB/s and the M3 Ultra has 819 GB/s. Notably, the Apple M series does not have FP4 support, so this could mean a significant performance improvement over Apple's offerings.
I don't understand why this isn't bigger news - this is a laptop SoC with actual gaming hardware running on ARM - unlike Apple's M series, which tend to have rather underwhelming perf in games compared to what the specs would suggest, finally we can have a thin-and-light with an efficient gaming GPU.
Considering how much Valve invested into ARM emulation, it's quite possible the next Steam Deck/handheld will use a variation of this (or at least there will be one using this as the SoC).
It's seeming to be going to be an another DGX Sparks that aren't so faster than maxed out Mac Studio, nor cheaper than 4x Blackwell on a workstation, nor cloud tokens. That's why.
Yeah the 1 PF is only for sparse models (only half otherwise), and it seems to have serious hardware issues: https://x.com/ID_AA_Carmack/status/1982831774850748825
Well, we don't have any information on cost, battery life or performance yet, which all matter. Could very well run laps around the M series at half the battery life and twice the cost.
Doubtful the slug in the room is Microsoft’s actual support see Qualcomm’s experience, not what Microsoft says in a media guide but what their actual support is when the hardware hits the street.