H100 SXM5 64 GB vs Radeon RX 5900
Contents
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 | RDNA 2.0 (2020−2025) | Hopper (2022−2024) |
| GPU code name | Navi 21 | GH100 |
| Market segment | Desktop | Workstation |
| Release date | no data | 21 March 2023 (2 years ago) |
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 | 4096 | 16896 |
| Core clock speed | no data | 1665 MHz |
| Boost clock speed | 1635 MHz | 1980 MHz |
| Number of transistors | 21,000 million | 80,000 million |
| Manufacturing process technology | 7 nm | 5 nm |
| Power consumption (TDP) | 300 Watt | 700 Watt |
| Texture fill rate | 418.6 | 1,045 |
| Floating-point processing power | 13.39 TFLOPS | 66.91 TFLOPS |
| ROPs | 96 | 24 |
| TMUs | 256 | 528 |
| Tensor Cores | no data | 528 |
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 4.0 x16 | PCIe 5.0 x16 |
| Width | 2-slot | SXM Module |
| Supplementary power connectors | 2x 8-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 | GDDR6 | HBM3 |
| Maximum RAM amount | 12 GB | 64 GB |
| Memory bus width | 384 Bit | 3072 Bit |
| Memory clock speed | 14000 MHz | 1313 MHz |
| Memory bandwidth | 672.0 GB/s | 2.02 TB/s |
| Resizable BAR | + | + |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | 1x HDMI, 3x DisplayPort | No outputs |
| HDMI | + | - |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_1) | N/A |
| Shader Model | no data | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | no data | 3.0 |
| Vulkan | - | N/A |
| CUDA | - | 9.0 |
| DLSS | - | + |
Pros & cons summary
| Maximum RAM amount | 12 GB | 64 GB |
| Chip lithography | 7 nm | 5 nm |
| Power consumption (TDP) | 300 Watt | 700 Watt |
RX 5900 has 133.3% lower power consumption.
H100 SXM5 64 GB, on the other hand, has a 433.3% higher maximum VRAM amount, and a 40% more advanced lithography process.
We couldn't decide between Radeon RX 5900 and H100 SXM5 64 GB. We've got no test results to judge.
Be aware that Radeon RX 5900 is a desktop graphics card while H100 SXM5 64 GB is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
