GeForce RTX 4070 Ti vs H100 SXM5
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | not rated | 12 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 53.66 |
| Power efficiency | no data | 20.55 |
| Architecture | Hopper (2022−2024) | Ada Lovelace (2022−2024) |
| GPU code name | GH100 | AD104 |
| Market segment | Workstation | Desktop |
| Release date | 22 March 2022 (4 years ago) | 3 January 2023 (3 years ago) |
| Launch price (MSRP) | no data | $799 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
Currently popular graphics cards are shown for comparison.
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.
| Pipelines / CUDA cores | 8448 | 7680 |
| Core clock speed | 1065 MHz | 2310 MHz |
| Boost clock speed | 1780 MHz | 2610 MHz |
| Number of transistors | 80,000 million | 35,800 million |
| Manufacturing process technology | 4 nm | 4 nm |
| Power consumption (TDP) | 700 Watt | 285 Watt |
| Texture fill rate | 939.8 | 626.4 |
| Floating-point processing power | 30.07 TFLOPS | 40.09 TFLOPS |
| ROPs | 24 | 80 |
| TMUs | 528 | 240 |
| Tensor Cores | 528 | 240 |
| Ray Tracing Cores | no data | 60 |
| L1 Cache | 24.8 MB | 7.5 MB |
| L2 Cache | 50 MB | 48 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 x16 |
| Length | no data | 285 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 | GDDR6X |
| Maximum RAM amount | 80 GB | 12 GB |
| Memory bus width | 5120 Bit | 192 Bit |
| Memory clock speed | 1500 MHz | 1313 MHz |
| Memory bandwidth | 1,920 GB/s | 504.2 GB/s |
| Shared memory | - | - |
| 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 | 1x HDMI 2.1, 3x DisplayPort 1.4a |
| HDMI | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | N/A | 12 Ultimate (12_2) |
| Shader Model | N/A | 6.7 |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | 9.0 | 8.9 |
| DLSS | + | + |
Pros & cons summary
| Recency | 22 March 2022 | 3 January 2023 |
| Maximum RAM amount | 80 GB | 12 GB |
| Power consumption (TDP) | 700 Watt | 285 Watt |
H100 SXM5 has a 567% higher maximum VRAM amount.
RTX 4070 Ti, on the other hand, has an age advantage of 9 months, and 146% lower power consumption.
We couldn't decide between H100 SXM5 and GeForce RTX 4070 Ti. We've got no test results to judge.
Be aware that H100 SXM5 is a workstation graphics card while GeForce RTX 4070 Ti is a desktop one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
