H200 NVL vs Tesla K20X
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 | Kepler (2012−2018) | Hopper (2022−2024) |
| GPU code name | GK110 | GH100 |
| Market segment | Workstation | Workstation |
| Release date | 12 November 2012 (13 years ago) | 18 November 2024 (1 year ago) |
| Launch price (MSRP) | $7,699 | 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. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.
| Pipelines / CUDA cores | 2688 | 16896 |
| Core clock speed | 732 MHz | 1365 MHz |
| Boost clock speed | no data | 1785 MHz |
| Number of transistors | 7,080 million | 80,000 million |
| Manufacturing process technology | 28 nm | 5 nm |
| Power consumption (TDP) | 235 Watt | 600 Watt |
| Texture fill rate | 164.0 | 942.5 |
| Floating-point processing power | 3.935 TFLOPS | 60.32 TFLOPS |
| ROPs | 48 | 24 |
| TMUs | 224 | 528 |
| Tensor Cores | no data | 528 |
| L1 Cache | 224 KB | 33 MB |
| L2 Cache | 1536 KB | 50 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 3.0 x16 | PCIe 5.0 x16 |
| Length | 267 mm | 267 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 1x 6-pin + 1x 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 | GDDR5 | HBM3e |
| Maximum RAM amount | 6 GB | 141 GB |
| Memory bus width | 384 Bit | 6144 Bit |
| Memory clock speed | 1300 MHz | 1593 MHz |
| Memory bandwidth | 249.6 GB/s | 4.89 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 | No outputs | No outputs |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (11_0) | N/A |
| Shader Model | 5.1 | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 1.2 | 3.0 |
| Vulkan | 1.1.126 | N/A |
| CUDA | 3.5 | 9.0 |
| DLSS | - | + |
Pros & cons summary
| Recency | 12 November 2012 | 18 November 2024 |
| Maximum RAM amount | 6 GB | 141 GB |
| Chip lithography | 28 nm | 5 nm |
| Power consumption (TDP) | 235 Watt | 600 Watt |
Tesla K20X has 155% lower power consumption.
H200 NVL, on the other hand, has an age advantage of 12 years, a 2250% higher maximum VRAM amount, and a 460% more advanced lithography process.
We couldn't decide between Tesla K20X and H200 NVL. 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.
