94GB · AI Score 67.0/100 · anchored estimate vs 51 measured cards
67 AI Score Includes estimates
We have not run NVIDIA H100 NVL 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 H100 NVL should deliver about 307.8 tokens/sec. Stepping up to Qwen3 32B it should hold roughly 87.1 tok/s. The full Llama 3.3 70B still runs, at about 48.2 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 94GB. There is no model in our suite this card has to turn down. NVIDIA H100 NVL isn't a retail purchase for most people. It's rented by the hour. You can run this exact card on RunPod.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3 4B | 364.7 tok/s | estimated | Est. |
| Llama 3.1 8B | 307.8 tok/s | estimated | Est. |
| Qwen2.5-Coder 14B | 170.3 tok/s | estimated | Est. |
| Qwen3 32B | 87.1 tok/s | estimated | Est. |
| Llama 3.3 70B | 48.2 tok/s | estimated | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Diffusion XL | 34.58 images/min | estimated | Est. |
| Z-Image Turbo | 22.13 images/min | estimated | Est. |
| FLUX.1 dev | 9.06 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 | 94GB HBM3 |
| Memory bus | 6016-bit |
| Memory bandwidth | 3938 GB/s |
| Boost clock | 1,785 MHz |
| TDP | 400 W |
| Process | TSMC 4N |
| Interface | PCIe 5.0 x16 |
| Release date | 2023-03-21 |
| Launch MSRP | $29,000 |
NVIDIA H100 NVL scores 67.0/100, #4 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). #4 of 21 desktop cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| NVIDIA B300 | 140% | 93.8 | |
| NVIDIA B200 | 116% | 78 | |
| NVIDIA B100 | 100% | 67 | |
| NVIDIA H100 NVL | 100% | 67 | |
| NVIDIA GH200 Grace Hopper | 98% | 65.6 | |
| NVIDIA H200 | 97% | 65 | |
| NVIDIA H100 80GB HBM3 | 93% | 62.6 | |
| NVIDIA H800 80GB | 93% | 62.6 |
← All AI & Machine Learning GPU rankings
Whole-job timings, composed from our measured per-model results on this card.
| Workflow | Time | Energy | Basis |
|---|---|---|---|
| 24-frame storyboard | 81 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 |
| Full codebase review | 5.9 min | n/a | estimate, 0 of 1 stage measured |
| 10 short social clips | 6.7 min | n/a | estimate, 0 of 3 stages measured |
| 20 long-form articles | 9.7 min | n/a | estimate, 0 of 1 stage measured |
| 40-product photo shoot | 10.5 min | n/a | estimate, 0 of 2 stages measured |
| 100-photo restoration batch | 23.5 min | n/a | estimate, 0 of 1 stage measured |
This card is $29,000 to buy. The cheapest listed rate on RunPod is $2.590/hour, but that is the floor: we budget $3.108/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 9,331 GPU-hours. Below it you are paying for idle silicon.
| How you would use it | GPU-hours a year | Rental cost a year | Time to break even |
|---|---|---|---|
| 2 hours a day, hobby | 730 | $2,269 | 12.8 years |
| 8 hours a day, working on it | 2,920 | $9,075 | 3.2 years |
| 24/7, always-on agent | 8,760 | $27,226 | 1.1 years |
At hobby usage this card is very unlikely to pay for itself before it is superseded. Rent it. Rental figures include a 20% premium over the cheapest listed rate. Ignores electricity, resale and the fact that a rented card can be a newer one tomorrow.
Cheapest of the RunPod and Vast on-demand rates we see, sampled daily. Spot and interruptible pricing runs lower.