Tiwari: Blackwell GPUs achieve 90 to 100x inference efficiency over Hopper
Neil Tiwari · Who's Actually Funding the AI Buildout? · Feb 26, 2026 · at 14:50
Neil Tiwari of Magnetar Capital discusses GPU efficiency gains, citing SemiAnalysis findings regarding Nvidia's Blackwell architecture compared to Hopper GPUs.
0:00 / 0:18exact quote · 18.3s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“And so for the hoppers, the H 100 or H 200 series of GPUs into the Blackwells there was a claim made that it could be 30 times more efficient. And I think the data from, you know, some analysis showed that it was 90 to a hundred times more efficient in terms of inference performance.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Neil Tiwari
Tiwari: GPU Depreciation Doesn't Matter in Fully Amortizing Contract-Backed Debt
“First is, On that depreciation question, in these kind of debt structures, it doesn't really matter because the debt's fully paid off by the end of the debt term against committed contractual you know, contracts from investment grade counterparties.”
Tiwari: Hyperscaler AI CapEx Will Scale to Trillions Over Next Several Years
“And over the next several years you know, that scales to trillions of dollars, right?”
Tiwari: AI Compute Debt Uses Customer Cash Flows, Not GPUs, as Primary Collateral
“And I think what got missed was the GPUs themselves were actually like the second, second or tertiary level of collateral in those instruments. The primary collateral was the contracted cash flows from investment grade counterparties.”
Tiwari: There are no idle 'dark GPUs' in AI data centers
“And I think what you see here is I have, you know, you don't see any dark GPUs.”
Tiwari: GPU Debt Structures Amortize to Zero Over 4–5 Years With No Balloon Payment
“And in these structures, typically the payback period on the capex was roughly two to three years. And the structures themselves, the debt was over five years, you know, four to five years in length where the entire debt amortized during the outstanding period…”
Tiwari: Data center power and operations have replaced chips as primary bottleneck
“Well, you know, fast forward to twenty-twenty-six, and what we see is, you know, there is obviously more availability of chips, but to build and operate these, you know, data centers requires people, power, infrastructure, a lot of these things that have a lot…”