Radeon Instinct MI300X vs GeForce RTX 3070 Ti 8 GB GA102

#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)CDNA 3.0 (2023−2024)
GPU code nameGA102Aqua Vanjaram
Market segmentDesktopDesktop
Release date21 October 2022 (1 year ago)6 December 2023 (less than a 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 cores614419456
Core clock speed1575 MHz1000 MHz
Boost clock speed1770 MHz2100 MHz
Number of transistors28,300 million153,000 million
Manufacturing process technology8 nm5 nm
Power consumption (TDP)290 Watt750 Watt
Texture fill rate339.82,554
Floating-point processing power21.75 TFLOPS81.72 TFLOPS
ROPs96no data
TMUs1921216
Tensor Cores1921216
Ray Tracing Cores48no 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-slotOAM Module
Supplementary power connectors1x 12-pinNone

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 typeGDDR6XHBM3
Maximum RAM amount8 GB192 GB
Memory bus width256 Bit8192 Bit
Memory clock speed1188 MHz2525 MHz
Memory bandwidth608.3 GB/s5,171 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 Connectors1x HDMI 2.1, 3x DisplayPort 1.4aNo outputs
HDMI+-

API compatibility

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
OpenCL3.03.0
Vulkan1.3N/A
CUDA8.6-

Pros & cons summary


Recency 21 October 2022 6 December 2023
Maximum RAM amount 8 GB 192 GB
Chip lithography 8 nm 5 nm
Power consumption (TDP) 290 Watt 750 Watt

RTX 3070 Ti 8 GB GA102 has 158.6% lower power consumption.

Instinct MI300X, on the other hand, has an age advantage of 1 year, a 2300% higher maximum VRAM amount, and a 60% more advanced lithography process.

We couldn't decide between GeForce RTX 3070 Ti 8 GB GA102 and Radeon Instinct MI300X. 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 GeForce RTX 3070 Ti 8 GB GA102
GeForce RTX 3070 Ti 8 GB GA102
AMD Radeon Instinct MI300X
Radeon Instinct MI300X

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.


4.1 75 votes

Rate GeForce RTX 3070 Ti 8 GB GA102 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
3.4 54 votes

Rate Radeon Instinct MI300X 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.