H200 NVL vs GeForce RTX 5090
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | not rated | not rated |
| Place by popularity | not in top-100 | not in top-100 |
| Architecture | Blackwell 2.0 (2025) | Hopper (2022−2024) |
| GPU code name | GB202 | GH100 |
| Market segment | Desktop | Workstation |
| Release date | 30 January 2025 | 18 November 2024 (less than a year ago) |
| Launch price (MSRP) | $1,999 | no data |
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 21760 | 16896 |
| Core clock speed | 2017 MHz | 1365 MHz |
| Boost clock speed | 2407 MHz | 1785 MHz |
| Number of transistors | 92,000 million | 80,000 million |
| Manufacturing process technology | 4 nm | 5 nm |
| Power consumption (TDP) | 575 Watt | 600 Watt |
| Texture fill rate | 1,637 | 942.5 |
| Floating-point processing power | 104.8 TFLOPS | 60.32 TFLOPS |
| ROPs | 192 | 24 |
| TMUs | 680 | 528 |
| Tensor Cores | 680 | 528 |
| Ray Tracing Cores | 170 | no data |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Interface | PCIe 5.0 x16 | PCIe 5.0 x16 |
| Length | 304 mm | 267 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 1x 16-pin | 8-pin EPS |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR7 | HBM3e |
| Maximum RAM amount | 32 GB | 141 GB |
| Memory bus width | 512 Bit | 5120 Bit |
| Memory clock speed | 2209 MHz | 1313 MHz |
| Memory bandwidth | 1.79 TB/s | 3.36 TB/s |
Connectivity and outputs
Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.
| Display Connectors | 1x HDMI 2.1b, 3x DisplayPort 2.1b | No outputs |
| HDMI | + | - |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | N/A |
| Shader Model | 6.8 | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.4 | N/A |
| CUDA | 10.1 | 9.0 |
Pros & cons summary
| Recency | 30 January 2025 | 18 November 2024 |
| Maximum RAM amount | 32 GB | 141 GB |
| Chip lithography | 4 nm | 5 nm |
| Power consumption (TDP) | 575 Watt | 600 Watt |
RTX 5090 has an age advantage of 2 months, a 25% more advanced lithography process, and 4.3% lower power consumption.
H200 NVL, on the other hand, has a 340.6% higher maximum VRAM amount.
We couldn't decide between GeForce RTX 5090 and H200 NVL. We've got no test results to judge.
Be aware that GeForce RTX 5090 is a desktop card while H200 NVL is a workstation one.
Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
