Radeon Instinct MI300 vs H100 SXM5 96 GB

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
ArchitectureHopper (2022−2023)CDNA 3.0 (2023−2024)
GPU code nameGH100Aqua Vanjaram
Market segmentWorkstationWorkstation
Release date21 March 2023 (1 year ago)4 January 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 cores1689614080
Core clock speed1665 MHz1000 MHz
Boost clock speed1837 MHz1700 MHz
Number of transistors80,000 million153,000 million
Manufacturing process technology4 nm5 nm
Power consumption (TDP)700 Watt600 Watt
Texture fill rate969.91,496
Floating-point processing power62.08 TFLOPS47.87 TFLOPS
ROPs24no data
TMUs528880
Tensor Cores528880

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 5.0 x16PCIe 5.0 x16
Lengthno data267 mm
WidthSXM Module2-slot
Supplementary power connectors8-pin EPS2x 8-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 typeHBM3HBM3
Maximum RAM amount96 GB128 GB
Memory bus width5120 Bit8192 Bit
Memory clock speed1313 MHz1600 MHz
Memory bandwidth1,681 GB/s3,277 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 ConnectorsNo outputsNo outputs

API compatibility

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

DirectXN/AN/A
Shader ModelN/AN/A
OpenGLN/AN/A
OpenCL3.03.0
VulkanN/AN/A
CUDA9.0-

Pros & cons summary


Recency 21 March 2023 4 January 2023
Maximum RAM amount 96 GB 128 GB
Chip lithography 4 nm 5 nm
Power consumption (TDP) 700 Watt 600 Watt

H100 SXM5 96 GB has an age advantage of 2 months, and a 25% more advanced lithography process.

Instinct MI300, on the other hand, has a 33.3% higher maximum VRAM amount, and 16.7% lower power consumption.

We couldn't decide between H100 SXM5 96 GB and Radeon Instinct MI300. 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 H100 SXM5 96 GB
H100 SXM5 96 GB
AMD Radeon Instinct MI300
Radeon Instinct MI300

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.


3.8 51 vote

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

  • 1
  • 2
  • 3
  • 4
  • 5
4.6 25 votes

Rate Radeon Instinct MI300 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.