H100 SXM5 64 GB vs Radeon 660M

#ad 
Buy on Amazon
VS

Primary details

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

Place in the ranking565not rated
Place by popularity97not in top-100
Power efficiency14.78no data
ArchitectureRDNA 2.0 (2020−2025)Hopper (2022−2024)
GPU code nameRembrandt+GH100
Market segmentLaptopWorkstation
Release date3 January 2023 (2 years ago)21 March 2023 (2 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 cores38416896
Core clock speed1500 MHz1665 MHz
Boost clock speed1900 MHz1980 MHz
Number of transistors13,100 million80,000 million
Manufacturing process technology6 nm5 nm
Power consumption (TDP)40 Watt700 Watt
Texture fill rate45.601,045
Floating-point processing power1.459 TFLOPS66.91 TFLOPS
ROPs1624
TMUs24528
Tensor Coresno data528
Ray Tracing Cores6no data
L0 Cache96 KBno data
L1 Cache128 KB33 MB
L2 Cache2 MB30 MB
L3 Cache8 MBno 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 x8PCIe 5.0 x16
Widthno dataSXM Module
Supplementary power connectorsNone8-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 typeSystem SharedHBM3
Maximum RAM amountSystem Shared64 GB
Memory bus widthSystem Shared3072 Bit
Memory clock speedSystem Shared1313 MHz
Memory bandwidthno data2.02 TB/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 ConnectorsPortable Device DependentNo outputs

API and SDK support

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

DirectX12 Ultimate (12_2)N/A
Shader Model6.7N/A
OpenGL4.6N/A
OpenCL2.03.0
Vulkan1.3N/A
CUDA-9.0
DLSS-+

Pros & cons summary


Recency 3 January 2023 21 March 2023
Chip lithography 6 nm 5 nm
Power consumption (TDP) 40 Watt 700 Watt

Radeon 660M has 1650% lower power consumption.

H100 SXM5 64 GB, on the other hand, has an age advantage of 2 months, and a 20% more advanced lithography process.

We couldn't decide between Radeon 660M and H100 SXM5 64 GB. We've got no test results to judge.

Be aware that Radeon 660M is a notebook graphics card while H100 SXM5 64 GB is a workstation one.

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.


AMD Radeon 660M
Radeon 660M
NVIDIA H100 SXM5 64 GB
H100 SXM5 64 GB

Other comparisons

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.


3.7 442 votes

Rate Radeon 660M on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
5 4 votes

Rate H100 SXM5 64 GB on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Comments

Here you can give us your opinion about Radeon 660M or H100 SXM5 64 GB, agree or disagree with our ratings, or report errors or inaccuracies on the site.