NVIDIA H800
The export-compliant H100 for China — and the chip DeepSeek trained V3 on.
You're looking at a chip record: what this processor is, its key specs, who designs, manufactures and supplies its parts, and where it gets used.
The H800 kept the H100's FP8 tensor throughput but cut NVLink bandwidth to about 400 GB/s and sharply reduced FP64 to satisfy the 2022 export rules. DeepSeek's V3 technical report describes training on a 2,048-GPU H800 cluster, engineering around the interconnect limits — the chip is now shorthand for how constrained hardware shaped Chinese frontier labs. Banned by the October 2023 rules.
Specifications & key facts
Each figure is labeled by basis: vendor spec, vendor claim, reported, estimate, or official. "Not publicly disclosed" means exactly that — we never invent values.
Overview
Physical
Compute
How this connects to the rest of the stack
This record's links at a glance — click a group to jump to it.
Designed by
Manufactured by
Used to train
Based on
Related
Sources
DeepSeek-V3 technical report (H800 cluster) ↗
Record reviewed as of 2026-01-15 — see Methodology.