Comment by sho
8 hours ago
So, that gets us to about where nVidia was with Ampere in 2020. Let's hope the M7 catches us up with at least Hopper.
8 hours ago
So, that gets us to about where nVidia was with Ampere in 2020. Let's hope the M7 catches us up with at least Hopper.
While true, the news here is the size of the unified RAM. Nvidia only exceeded 256GB RAM in the 2025 B300 - 288GB. The B300 alone (without the baseboard/PSU/chassis/wiring/CPUs/system RAM/etc) is at least 700% more expensive. This enables large language models on consumer hardware. 1200GB/s is plenty for many tasks.
I wonder if the inference acceleration companies will ever produce a consumer product
> 1200GB/s is plenty for many tasks.
This + due to the hardware being so prohibitively expensive, we're seeing software optimizations happening. Like that dflash2 stuff for example, or an LRU for MoE and all that kind of stuff.