A30X vs H100 SXM5
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 | Hopper (2022−2024) | Ampere (2020−2025) |
| GPU code name | GH100 | GA100 |
| Market segment | Workstation | Workstation |
| Release date | 22 March 2022 (3 years ago) | 12 April 2021 (4 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 | 8448 | 3584 |
| Core clock speed | 1065 MHz | 1035 MHz |
| Boost clock speed | 1780 MHz | 1440 MHz |
| Number of transistors | 80,000 million | 54,200 million |
| Manufacturing process technology | 4 nm | 7 nm |
| Power consumption (TDP) | 700 Watt | 230 Watt |
| Texture fill rate | 939.8 | 322.6 |
| Floating-point processing power | 30.07 TFLOPS | 10.32 TFLOPS |
| ROPs | 24 | 96 |
| TMUs | 528 | 224 |
| Tensor Cores | 528 | 224 |
| L1 Cache | 24.8 MB | 10.5 MB |
| L2 Cache | 50 MB | 24 MB |
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 4.0 x8 |
| Length | no data | 267 mm |
| Width | no data | 2-slot |
| Supplementary power connectors | 8-pin EPS | 1x 16-pin |
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 | HBM3 | HBM2e |
| Maximum RAM amount | 80 GB | 24 GB |
| Memory bus width | 5120 Bit | 3072 Bit |
| Memory clock speed | 1500 MHz | 1593 MHz |
| Memory bandwidth | 1,920 GB/s | 1,223 GB/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 | No outputs | No outputs |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | N/A | N/A |
| Shader Model | N/A | N/A |
| OpenGL | N/A | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | N/A |
| CUDA | 9.0 | 8.0 |
| DLSS | + | + |
Pros & cons summary
| Recency | 22 March 2022 | 12 April 2021 |
| Maximum RAM amount | 80 GB | 24 GB |
| Chip lithography | 4 nm | 7 nm |
| Power consumption (TDP) | 700 Watt | 230 Watt |
H100 SXM5 has an age advantage of 11 months, a 233.3% higher maximum VRAM amount, and a 75% more advanced lithography process.
A30X, on the other hand, has 204.3% lower power consumption.
We couldn't decide between H100 SXM5 and A30X. We've got no test results to judge.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
