H100 SXM5: specs and benchmarks

VS

Summary

NVIDIA started H100 SXM5 sales 22 March 2022. This is a Hopper architecture desktop card based on 4 nm manufacturing process and primarily aimed at designers. 80 GB of HBM3 memory clocked at 1.5 GHz are supplied, and together with 5120 Bit memory interface this creates a bandwidth of 1,920 GB/s.

Compatibility-wise, this is a graphics card attached via PCIe 5.0 x16 interface. 8-pin EPS power connector is required, and power consumption is at 700 Watt.

Primary details

Some basic facts about H100 SXM5: architecture, market segment, release date etc.

Place in the rankingnot rated
Place by popularitynot in top-100
ArchitectureHopper (2022−2023)
GPU code nameGH100
Market segmentWorkstation
Release date22 March 2022 (2 years ago)

Detailed specifications

H100 SXM5's specs such as number of shaders, GPU base clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of H100 SXM5's performance, but for precise assessment you have to consider its benchmark and gaming test results.

Pipelines / CUDA cores8448of 21760 (GeForce RTX 5090)
Core clock speed1065 MHzof 2670 MHz (Arc B580)
Boost clock speed1780 MHzof 3599 MHz (Radeon RX 7990 XTX)
Number of transistors80,000 millionof 208,000 million (B200 SXM 192 GB)
Manufacturing process technology4 nmof 3 nm (Arc Graphics 140V)
Power consumption (TDP)700 Wattof 2400 Watt (Data Center GPU Max Subsystem)
Texture fill rate939.8of 2,554 (Radeon Instinct MI300X)
Floating-point processing power30.07 TFLOPSof 109.7 (GeForce RTX 5090)
ROPs24of 192 (Radeon RX 7900 XTX)
TMUs528of 1280 (Data Center GPU Max NEXT)
Tensor Cores528of 1216 (Radeon Instinct MI300X)

Form factor & compatibility

This section provides details about the physical dimensions of H100 SXM5 and its compatibility with other computer components. This information is useful when selecting a computer configuration or upgrading an existing one. For desktop graphics cards, it includes details about the interface and bus (for motherboard compatibility) and additional power connectors (for power supply compatibility).

InterfacePCIe 5.0 x16
Supplementary power connectors8-pin EPS

VRAM capacity and type

Parameters of memory installed on H100 SXM5: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors have no dedicated memory and use a shared part of system RAM instead.

Memory typeHBM3
Maximum RAM amount80 GBof 294912 (Radeon Instinct MI325X)
Memory bus width5120 Bitof 8192 Bit (Radeon Instinct MI250X)
Memory clock speed1500 MHzof 20000 (RTX 5000 Ada Generation Mobile)
Memory bandwidth1,920 GB/sof 5,171 GB/s (Radeon Instinct MI300X)

Connectivity and outputs

Types and number of video connectors present on H100 SXM5. As a rule, this section is relevant only for desktop reference graphics cards, since for notebook ones the availability of certain video outputs depends on the laptop model, while non-reference desktop models can (though not necessarily will) bear a different set of video ports.

Display ConnectorsNo outputs

API compatibility

APIs supported by H100 SXM5, sometimes including their particular versions.

DirectXN/A
Shader ModelN/A
OpenGLN/Aof 4.6 (GeForce RTX 4090)
OpenCL3.0
VulkanN/A
CUDA9.0

Benchmark performance

Synthetic benchmark performance of H100 SXM5. The combined score is measured on a 0-100 point scale.



We have no data on H100 SXM5 benchmark results.


AMD equivalent

According to our data, the closest AMD alternative to H100 SXM5 is Radeon PRO W7700.

Similar GPUs

Here is our recommendation of several graphics cards that are more or less close in performance to the one reviewed.

Recommended processors

These processors are most commonly used with H100 SXM5 according to our statistics.

All comparisons with H100 SXM5

Community ratings

Here you can see the user rating of the graphics card, as well as rate it yourself.


4.2 27 votes

Rate H100 SXM5 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Questions & comments

Here you can ask a question about H100 SXM5, agree or disagree with our judgements, or report an error or mismatch.