H100 SXM5 96 GB vs A40 PCIe

#ad 
Buy on Amazon
VS

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the rankingnot ratednot rated
Place by popularitynot in top-100not in top-100
ArchitectureAmpere (2020−2024)Hopper (2022−2023)
GPU code nameGA102GH100
Market segmentWorkstationWorkstation
Release date5 October 2020 (4 years ago)21 March 2023 (1 year 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 cores1075216896
Core clock speed1305 MHz1665 MHz
Boost clock speed1755 MHz1837 MHz
Number of transistors28,300 million80,000 million
Manufacturing process technology8 nm4 nm
Power consumption (TDP)300 Watt700 Watt
Texture fill rate589.7969.9
Floating-point processing power37.74 TFLOPS62.08 TFLOPS
ROPs11224
TMUs336528
Tensor Cores336528
Ray Tracing Cores84no data

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).

InterfacePCIe 4.0 x16PCIe 5.0 x16
Length267 mmno data
Width2-slotSXM Module
Supplementary power connectors8-pin EPS8-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 typeGDDR6HBM3
Maximum RAM amount48 GB96 GB
Memory bus width384 Bit5120 Bit
Memory clock speed1812 MHz1313 MHz
Memory bandwidth695.8 GB/s1,681 GB/s

Connectivity and outputs

Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.

Display Connectors3x DisplayPortNo outputs

API compatibility

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX12 Ultimate (12_2)N/A
Shader Model6.5N/A
OpenGL4.6N/A
OpenCL2.03.0
Vulkan1.2N/A
CUDA8.69.0

Pros & cons summary


Recency 5 October 2020 21 March 2023
Maximum RAM amount 48 GB 96 GB
Chip lithography 8 nm 4 nm
Power consumption (TDP) 300 Watt 700 Watt

A40 PCIe has 133.3% lower power consumption.

H100 SXM5 96 GB, on the other hand, has an age advantage of 2 years, a 100% higher maximum VRAM amount, and a 100% more advanced lithography process.

We couldn't decide between A40 PCIe and H100 SXM5 96 GB. We've got no test results to judge.


Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.

Vote for your favorite

Do you think we are right or mistaken in our choice? Vote by clicking "Like" button near your favorite graphics card.


NVIDIA A40 PCIe
A40 PCIe
NVIDIA H100 SXM5 96 GB
H100 SXM5 96 GB

Comparisons with similar GPUs

We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.

Community ratings

Here you can see the user ratings of the compared graphics cards, as well as rate them yourself.


4.6 88 votes

Rate A40 PCIe on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
3.8 57 votes

Rate H100 SXM5 96 GB on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Questions & comments

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