Specifications Compared
| Spec | GH200 | RTX 5090 |
|---|---|---|
| TDP | 900W | 575W |
| VRAM | 96 GB | 32 GB |
| CUDA Cores | 16,896 | 21,760 |
| FP4 (dense) | Not published | 1,676 TFLOPS |
| FP8 (dense) | 1,979 TFLOPS | 419 TFLOPS |
| Memory Type | HBM3 | GDDR7 |
| Architecture | Hopper | Blackwell |
| FP16 (dense) | 989 TFLOPS | 209.5 TFLOPS |
| Form Factors | SXM | PCIe |
| INT8 (dense) | 1,979 TOPS | 838 TOPS |
| Interconnect | NVLink-C2C, PCIe 5.0 | PCIe 5.0 |
| Tensor Cores | 528 | 680 |
| FP32 Performance | 67 TFLOPS | 104.8 TFLOPS |
| FP64 Performance | 34 TFLOPS | 1.6 TFLOPS |
| Memory Bandwidth | 4,000 GB/s | 1,792 GB/s |
| FP4 (with sparsity) | Not published | 3,352 TFLOPS |
| FP8 (with sparsity) | 3,958 TFLOPS | 838 TFLOPS |
| FP16 (with sparsity) | 1,979 TFLOPS | 419 TFLOPS |
| INT8 (with sparsity) | 3,958 TOPS | 1,676 TOPS |
Performance Analysis
Dense FP16 performance on the GH200 reaches 989 TFLOPS while the RTX 5090 reaches 209.5 TFLOPS. With sparsity the GH200 reaches 1979 TFLOPS and the RTX 5090 reaches 419 TFLOPS. The higher dense FP16 figure on the GH200 supports faster matrix operations during training of large models. The higher FP32 figure of 104.8 TFLOPS on the RTX 5090 benefits precision sensitive single precision workloads. Memory bandwidth of 4000 GB/s on the GH200 versus 1792 GB/s on the RTX 5090 allows larger batch sizes before memory becomes the limit. The 96 GB capacity on the GH200 further extends feasible batch sizes compared with the 32 GB capacity on the RTX 5090.
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.
GH200
GH200 is not offered on-demand by any provider we track right now. See the GH200 rental page for last-seen listed prices and a price alert.
Notify me when GH200 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold.
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 GH200
The GH200 suits workloads that require 96 GB HBM3 capacity and 4000 GB/s bandwidth. Scientific computing tasks benefit from these specifications along with dense FP16 at 989 TFLOPS. LLM training also favors the GH200 when batch sizes exceed limits imposed by 32 GB VRAM.
When to Choose the RTX 5090
Lower TDP of 575W reduces power draw in dense deployments. PCIe form factor simplifies integration in standard servers compared with SXM.
Use Cases
The GH200 supplies 989 TFLOPS dense FP16 and 4000 GB/s bandwidth to handle large batches.
The GH200 supplies 1979 TFLOPS with sparsity in FP16 and 96 GB capacity for long context lengths.
The GH200 supplies 1979 TOPS dense INT8 and 4000 GB/s bandwidth to process large datasets efficiently.
The RTX 5090 supplies 104.8 TFLOPS FP32 and lower 575W TDP for image generation workloads.
The GH200 supplies 4000 GB/s bandwidth and 96 GB HBM3 for memory intensive simulations.
Frequently Asked Questions
How does FP16 dense performance compare?▾
The GH200 reaches 989 TFLOPS dense FP16 while the RTX 5090 reaches 209.5 TFLOPS dense FP16.
Which GPU has higher memory bandwidth?▾
The GH200 has 4000 GB/s bandwidth while the RTX 5090 has 1792 GB/s bandwidth.
What are the TDP values for each GPU?▾
The GH200 has a TDP of 900W while the RTX 5090 has a TDP of 575W.
Does the GH200 support higher sparse FP8 performance?▾
The GH200 reaches 3958 TFLOPS with sparsity in FP8 while the RTX 5090 reaches 838 TFLOPS with sparsity in FP8.
Which GPU offers higher FP32 performance?▾
The RTX 5090 reaches 104.8 TFLOPS FP32 while the GH200 reaches 67 TFLOPS FP32.
Which is cheaper to rent, the GH200 or the RTX 5090?▾
Cloud rental prices for both the GH200 and RTX 5090 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 GH200 have compared to the RTX 5090?▾
The GH200 has 96 GB of HBM3 memory. The RTX 5090 has 32 GB of GDDR7 memory.
Can I find GH200 and RTX 5090 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 GH200 and the RTX 5090?▾
The GH200 uses the Hopper architecture (2023) while the RTX 5090 uses Blackwell (2025). The GH200 delivers 4.7x the dense FP16 throughput (989 vs 209.5 TFLOPS, both without sparsity) and 2.2x the memory bandwidth of the RTX 5090.
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 GH200 and the RTX 5090. 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 GH200 Grace HopperEvery current offer by provider, daily price history and a price alert.
- Rent RTX 5090Every 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.