AI chip · NVIDIA
NVIDIA H800
China-specific export-compliant variant of the H100 Tensor Core GPU. Cut the NVLink bandwidth (from 900 GB/s to 400 GB/s) to fit under the Oct 2022 BIS interconnect ceiling. Superseded Oct 2023 when BIS closed that workaround.
Market position
The chip NVIDIA built to keep selling into China under the Oct 7 2022 BIS rule. Identical compute silicon to H100, throttled interconnect. Big Chinese buyers (Alibaba, Baidu, Tencent, ByteDance) took delivery through 2023 until the Oct 17 2023 rule made it non-exportable too.
Efficiency and power
How much work you get per watt and per dollar, and how much power a full rack draws.
- Perf per watt
- 2.83 FP8 TFLOPS/W1,979 TFLOPS ÷ 700 W = 2.83
What fits in 80 GB
Which open-source LLMs run on one NVIDIA H800, by precision. Weights only: add roughly 15% headroom for real serving. If a model does not fit at FP16, try INT8 or INT4 (smaller quality trade-off than most people expect).
| Model | Params | FP16 | INT8 | INT4 |
|---|---|---|---|---|
| Llama 3.1 8B dense | 8 B | 16 GB ✓ | 8 GB ✓ | 4 GB ✓ |
| Llama 3.1 70B dense | 70 B | 140 GB ✗ | 70 GB ✓ | 35 GB ✓ |
| Llama 3.1 405B dense | 405 B | 810 GB ✗ | 405 GB ✗ | 203 GB ✗ |
| Llama 3.3 70B dense | 70 B | 140 GB ✗ | 70 GB ✓ | 35 GB ✓ |
| DeepSeek V3 MoE (671B total, 37B active per token) | 671 B | 1342 GB ✗ | 671 GB ✗ | 336 GB ✗ |
| DeepSeek R1 MoE (671B total, 37B active per token) | 671 B | 1342 GB ✗ | 671 GB ✗ | 336 GB ✗ |
| Qwen 2.5 7B dense | 7 B | 14 GB ✓ | 7 GB ✓ | 4 GB ✓ |
| Qwen 2.5 72B dense | 72 B | 144 GB ✗ | 72 GB ✓ | 36 GB ✓ |
| Mixtral 8x7B MoE (46.7B total, 12.9B active per token) | 46.7 B | 93 GB ✗ | 47 GB ✓ | 23 GB ✓ |
| Mixtral 8x22B MoE (141B total, 39B active per token) | 141 B | 282 GB ✗ | 141 GB ✗ | 71 GB ✓ |
| Gemma 2 27B dense | 27 B | 54 GB ✓ | 27 GB ✓ | 14 GB ✓ |
| Command R+ dense | 104 B | 208 GB ✗ | 104 GB ✗ | 52 GB ✓ |
| Kimi K2 MoE (1T total, 32B active per token) | 1000 B | 2000 GB ✗ | 1000 GB ✗ | 500 GB ✗ |
Math: FP16 = params × 2 bytes; INT8 = params × 1 byte; INT4 = params × 0.5 bytes. MoE models sum every expert (full weights on disk), not the per-token active subset.
Export controls
US Commerce Department rules that restrict where NVIDIA H800 can be sold. Effective dates and full text below, with the official Federal Register filings and news coverage for each.
The US Bureau of Industry and Security's Oct 7 2022 interim final rule restricted export of advanced AI accelerators to China, keyed to a performance threshold (>=4,800 TOPS or >=600 GB/s interconnect). Directly blocked NVIDIA A100 and H100 sales to Chinese entities without a license, triggering the A800 and H800 China-specific variants NVIDIA released within weeks.
Sources: BIS press release, Oct 7 2022 · Federal Register, Oct 13 2022 (rule text)
The Oct 17 2023 update closed the workaround NVIDIA used with A800 and H800: BIS replaced the interconnect-bandwidth threshold with a performance-density metric (total processing performance x performance density) and added a Notified Advanced Computing regime for chips that fell just below the ceiling. Direct effect: A800 and H800 could no longer be exported to China. Triggered NVIDIA's H20 as the next-generation China-specific variant.
Sources: BIS press release, Oct 17 2023 · Federal Register, Oct 25 2023 (rule text)
Common questions
How much does NVIDIA H800 cost?
NVIDIA H800 doesn't have a public launch list price. Vendors like this one usually price through direct sales rather than a public sheet. See list price per TFLOP for chips that do publish.
How much memory does NVIDIA H800 have?
80 GB of HBM3, running at 3,350 GB/s. Straight from the vendor datasheet. See chips with the most memory for context.
How much power does one NVIDIA H800 draw?
700 W at the chip. A full server draws more once you add CPU, memory, networking and cooling: see the rack power number above. Compare to other chips on perf-per-watt.
Which open-source LLMs fit on one NVIDIA H800?
Of 13 open-source LLMs we track, 3 fit at FP16, 7 at INT8, and 9 at INT4 (for example Llama 3.1 8B, Llama 3.1 70B and Llama 3.3 70B). Full table above with each model's memory need.
Is NVIDIA H800 subject to US export controls?
Yes. 2 US Commerce Department rules restrict where this chip can be sold, most recently BIS Oct 17 2023 tightening of AI chip export controls (2023-10-17). Details and effective dates in the export-control section above.
Key facts
- Class
- Compute SoC (AI accelerator)
- Designer
- NVIDIA
- Safety-critical?
- No (data-center inference / training)
- Record as of
- 2026-09-27
Specifications (9 fields, click to expand)
Straight from the vendor datasheet. Dense throughput shown first; sparse (2:4) numbers in parentheses where the vendor publishes them. Full datasheet linked below.
- Process node
- TSMC 4N
- TDP
- 700 W
- Memory
- 80 GB HBM3
- Memory bandwidth
- 3,350 GB/s
- FP16 (dense)
- 989 TFLOPS
- FP8 (dense)
- 1,979 TFLOPS
- Form factor
- SXM5
- Announced
- 2022-11-01
- Released
- 2023-03-01
Source: vendor datasheet
Generation
Foundry & process
- Process node
- TSMC 4N
Sources
Adoption rows appear as we confirm each chip-in-robot pairing from a public source. See every chip we track for the full catalog or the NVIDIA page.