NVIDIA announces H200
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
H200 announced — 141 GB of HBM3e, 4.8 TB/s
Why it matters
The first product to put memory capacity and bandwidth, rather than compute, forward as its generational differentiator
Source — Primary sources first; secondary reports are labelled “Press”
Officialnvidianews.nvidia.comhttps://nvidianews.nvidia.com/news/nvidia-supercharges-hopper-the-worlds-leading-ai-computing-platformAdded in Week 35, 2026 · See that week
On the map — ⑧ Inference Infrastructure line
- Previous stopTensorRT-LLM
- This recordH200
- Next stopSarathi-Serve