Specifications Compared
| Spec | H100 SXM5 | RTX 3090 |
|---|---|---|
| TDP | 700W | 350W |
| VRAM | 80 GB | 24 GB |
| CUDA Cores | 16,896 | 10,496 |
| FP8 (dense) | 1,979 TFLOPS | Not published |
| Memory Type | HBM3 | GDDR6X |
| Architecture | Hopper | Ampere |
| FP16 (dense) | 989 TFLOPS | 71 TFLOPS |
| Form Factors | SXM5 | PCIe |
| INT8 (dense) | 1,979 TOPS | 284 TOPS |
| Interconnect | NVLink, PCIe 5.0, InfiniBand | NVLink, PCIe 4.0 |
| Tensor Cores | 528 | 328 |
| FP32 Performance | 67 TFLOPS | 35.6 TFLOPS |
| FP64 Performance | 34 TFLOPS | Not published |
| Memory Bandwidth | 3,350 GB/s | 936 GB/s |
| FP8 (with sparsity) | 3,958 TFLOPS | Not published |
| FP16 (with sparsity) | 1,979 TFLOPS | 142 TFLOPS |
| INT8 (with sparsity) | 3,958 TOPS | 568 TOPS |
Performance Analysis
The FP16 dense throughput of 989 TFLOPS on the H100 SXM5 exceeds the 71 TFLOPS dense FP16 on the RTX 3090 by a substantial margin. This gap implies faster matrix operations during training and inference for models that fit within the respective memory limits. The FP32 figure of 67 TFLOPS on the H100 family contrasts with 35.6 TFLOPS on the RTX 3090 family. Memory bandwidth at 3350 GB/s for the H100 family permits larger batch sizes than the 936 GB/s available on the RTX 3090 family during data intensive tasks. Sparse FP16 performance reaches 1979 TFLOPS on the H100 family compared to 142 TFLOPS on the RTX 3090 family. The INT8 dense rating of 1979 TOPS on the H100 family stands against 284 TOPS on the RTX 3090 family.
Current On-Demand Offers
Cheapest secure on-demand offer per provider that is reported in stock right now, per GPU per hour; multi-GPU instances show the whole-instance price alongside. Deploy opens the DeployGPU console for providers on the platform, otherwise the provider's own site. Stock is rechecked every minute.
H100 SXM5
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| QuantaCloud | us-midwest-2 | 1 | $2.59 | — | Deploy |
| Massed Compute | us-central-3 | 1 | $2.73 | — | Deploy |
| Ori | dallas-2 | 1 | $2.90 | — | Deploy |
| LeaderGPU | The Netherlands | 8 | $3.59 | $28.75 | Deploy |
| Vast.ai | Czechia, CZ | 2 | $4.23 | $8.47 | Deploy |
9 providers in stock, 20 offers (cheapest per provider shown). All H100 SXM5 offers, price history and alerts
RTX 3090
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| LeaderGPU | The Netherlands | 8 | $0.29 | $2.29 | Deploy |
| Vast.ai | Finland, FI | 8 | $0.29 | $2.35 | Deploy |
2 providers in stock, 10 offers (cheapest per provider shown). All RTX 3090 offers, price history and alerts
Notify me when H100 SXM5 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $2.59/GPU-hr.
QuantaCloud
Comparing H-series providers? We broker across all of them.
Hopper stock changes by the hour and prices differ by provider. If you need 16+ GPUs reserved or a cluster in the next 90 days, we quote H-series or B300 inventory at partner rates: one quote, 24h turnaround.
When to Choose the H100 SXM5
The H100 SXM5 suits scenarios that demand the 80 GB HBM3 capacity and 989 TFLOPS FP16 dense performance. Applications involving large scale tensor computations benefit from the 3350 GB/s bandwidth and 700 W TDP allowance. Users requiring InfiniBand connectivity select this variant over alternatives with lower specifications.
When to Choose the RTX 3090
The RTX 3090 fits workloads constrained to 24 GB GDDR6X memory and 350 W TDP. Tasks that operate effectively with 71 TFLOPS FP16 dense throughput proceed without the higher power draw of 700 W. PCIe form factor installations align with this choice for standard server setups.
Use Cases
The 80 GB HBM3 memory and 989 TFLOPS FP16 dense performance support larger models than the 24 GB and 71 TFLOPS on the RTX 3090.
FP16 dense throughput of 989 TFLOPS combined with 3350 GB/s bandwidth enables higher throughput than the 71 TFLOPS and 936 GB/s on the RTX 3090.
The 80 GB capacity allows fine tuning of models that exceed the 24 GB limit of the RTX 3090 while using 989 TFLOPS FP16 dense.
The 24 GB GDDR6X memory and 350 W TDP suffice for typical diffusion workloads without requiring the 700 W TDP of the H100 SXM5.
FP32 performance of 67 TFLOPS and 3350 GB/s bandwidth accelerate simulations beyond the 35.6 TFLOPS and 936 GB/s of the RTX 3090.
Frequently Asked Questions
What is the TDP of the RTX 3090?▾
The RTX 3090 uses a 350 W TDP shared across its family. This figure stands against the 700 W TDP of the H100 family.
How does FP16 dense performance compare between these GPUs?▾
The H100 SXM5 reaches 989 TFLOPS FP16 dense while the RTX 3090 reaches 71 TFLOPS FP16 dense. The comparison uses only dense figures on both sides.
Which interconnects does the H100 SXM5 support?▾
The H100 SXM5 supports NVLink, PCIe 5.0, and InfiniBand. The RTX 3090 supports NVLink and PCIe 4.0 instead.
Which is cheaper to rent, the H100 SXM5 or the RTX 3090?▾
Cloud rental prices for both the H100 SXM5 and RTX 3090 vary by provider, configuration, and availability. This page shows live pricing from 25+ providers updated every 60 seconds. Scroll to the Live Cloud Pricing section to compare current rates.
How much VRAM does the H100 SXM5 have compared to the RTX 3090?▾
The H100 SXM5 has 80 GB of HBM3 memory. The RTX 3090 has 24 GB of GDDR6X memory.
Can I find H100 SXM5 and RTX 3090 GPUs available to rent right now?▾
Yes. This page shows real-time availability across 25+ cloud GPU providers. The Live Cloud Pricing section displays only in-stock offers with current pricing.
What is the main difference between the H100 SXM5 and the RTX 3090?▾
The H100 SXM5 uses the Hopper architecture (2022) while the RTX 3090 uses Ampere (2020). The H100 SXM5 delivers 13.9x the dense FP16 throughput (989 vs 71 TFLOPS, both without sparsity) and 3.6x the memory bandwidth of the RTX 3090.
Rent these GPUs
Each GPU page lists every current on-demand offer by provider, per GPU-hour, updated every minute.
Related comparisons
How this page is made
- Specifications come from the NVIDIA, AMD and Intel datasheets for the H100 SXM5 and the RTX 3090. Dense and sparse throughput are listed separately.
- Prices and availability are live: every offer shown is an in-stock, on-demand listing from a provider we track, rechecked every minute.
- The written comparison (overview, performance notes, when to choose each card, verdict, use cases and FAQ) was drafted with an AI model from the specification table above and passed an automated check that rejects any figure not in that table. It was last generated on . It contains no prices; those are always read live.
- Read how we collect the data, or report an error on this page.
Next steps
- Rent H100Every current offer by provider, daily price history and a price alert.
- Rent RTX 3090Every current offer by provider, daily price history and a price alert.
- GPU price indexHow on-demand prices for the major GPUs have moved, updated daily.
- All GPUsEvery GPU we track, with current lows and provider counts.