Hopper architecture
also referred to as: hopper · hoppers
4 statements across 4 episodes · 1 bullish · 2 bearish · 4 people on the record · first statement Aug 18, 2025 by Thomas Sohmers · said 4 times in 2 episodes since 2025 · across every show →
Mentions by year
brought up most by Philip Kiely (2), Chris Lattner (2)
tap a year for its mentions
2026 2 mentions in 1 episode
2025 2 mentions in 1 episode
Everything said about Hopper architecture, oldest first
Aug 18, 2025 bearish
Sohmers: NVIDIA Blackwell memory bandwidth efficiency will be lower than Hopper
“All indications are, even though they, you know, more than doubled the theoretical memory bandwidth going from Hopper to Blackwell, the actual percentage of theoretical that you can achieve is, again, going to be less than the previous generation”
Nov 25, 2025 bearish
Johnson: Nvidia Blackwell offers roughly same performance per watt as Hopper
“Like, if you look at the numbers, like, even going from Hopper to Blackwell, like, the performance per watt is about the same. They mostly make the number of transistors go up, and they make the chip size go up, and they make the power usage go up. But even fr…”
Jul 22, 2026 bullish
Aug 3, 2026
Unoptimized GLM-5.2 delivers a baseline 30 to 40 tokens per second
“So let's say you have, as a reasonable baseline, 30 or 40 tokens per second. You can achieve 10 X that. So like on GLM 5.2 if you want to get unquantized perhaps on hoppers even and you're just using an off the shelf inference engine with no particular optimiz…”