80GB · AI Score 62.6/100 · anchored estimate vs 51 measured cards
62.6 AI Score Includes estimates
We have not run NVIDIA H800 80GB on our bench. These figures are anchored estimates, interpolated per workload against the 51 GPUs we did measure (confidence: high (sibling silicon)). On Llama 3.1 8B (Q4_K_M) NVIDIA H800 80GB should deliver about 261.8 tokens/sec. Stepping up to Qwen3 32B it should hold roughly 74.1 tok/s. The full Llama 3.3 70B still runs, at about 41 tok/s. For image generation, SDXL should run near 17.29 it/s, and FLUX.1-dev at 4.23 it/s. All 12 workloads fit in 80GB. There is no model in our suite this card has to turn down.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3 4B | 310.3 tok/s | estimated | Est. |
| Llama 3.1 8B | 261.8 tok/s | estimated | Est. |
| Qwen2.5-Coder 14B | 144.8 tok/s | estimated | Est. |
| Qwen3 32B | 74.1 tok/s | estimated | Est. |
| Llama 3.3 70B | 41 tok/s | estimated | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Diffusion XL | 34.58 images/min | estimated | Est. |
| FLUX.1 dev | 9.06 images/min | estimated | Est. |
| Z-Image Turbo | 22.13 images/min | estimated | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| FLUX.1 Kontext dev | 4.26 images/min | estimated | Est. |
| Qwen-Image-Edit | 3.68 images/min | estimated | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| LTX-Video (distilled) | 17.47 frames/s | estimated | Est. |
| Wan 2.2 5B (720p) | 1.33 frames/s | estimated | Est. |
| Architecture | Hopper |
| CUDA cores | 16,896 |
| VRAM | 80GB HBM3 |
| Memory bus | 5120-bit |
| Memory bandwidth | 3350 GB/s |
| Boost clock | 1,980 MHz |
| TDP | 700 W |
| Process | TSMC 4N |
| Interface | SXM5 |
| Release date | 2022-11-01 |
| Launch MSRP | $35,000 |
NVIDIA H800 80GB scores 62.6/100, #7 of 102. It ran all 12 workloads. Figures are anchored estimates, not measurements, we flag that on every row.
100% = this card, AI & Machine Learning headline metric (AI Score). #7 of 21 datacenter cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| NVIDIA B100 | 107% | 67 | |
| NVIDIA GH200 Grace Hopper | 105% | 65.6 | |
| NVIDIA H200 | 104% | 65 | |
| NVIDIA H100 80GB HBM3 | 100% | 62.6 | |
| NVIDIA H800 80GB | 100% | 62.6 | |
| NVIDIA H100 NVL | 93% | 58.1 | |
| NVIDIA RTX PRO 6000 Blackwell Server Edition | 80% | 49.9 | |
| NVIDIA H100 PCIe | 80% | 49.8 | |
| NVIDIA A100 80GB SXM4 | 53% | 33.1 |
← All AI & Machine Learning GPU rankings
| Transistors | 80,000 million |
| Die size | 814 mm² |
| Process node | 4 nm |
| Fabricated by | TSMC |
| Transistor density | 98.3 million per mm² |
Denser than 90% of the 746 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.
Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.
Whole-job timings, composed from our measured per-model results on this card.
| Workflow | Time | Energy | Basis |
|---|---|---|---|
| 24-frame storyboard | 84 s | n/a | estimate, 0 of 2 stages measured |
| 60-second AI short film | 2 min | n/a | estimate, 0 of 3 stages measured |
| 6-panel comic page | 2.2 min | n/a | estimate, 0 of 3 stages measured |
| Character sheet, 12 poses | 2.9 min | n/a | estimate, 0 of 2 stages measured |
| Short social clips | 6.7 min | n/a | estimate, 0 of 3 stages measured |
| Full codebase review | 6.9 min | n/a | estimate, 0 of 1 stage measured |
| Product photo shoot | 10.5 min | n/a | estimate, 0 of 2 stages measured |
| Long-form article batch | 11.4 min | n/a | estimate, 0 of 1 stage measured |
| Photo restoration batch | 23.5 min | n/a | estimate, 0 of 1 stage measured |