GeForce RTX 4080 and Radeon Instinct MI300 - video card comparison
GeForce RTX 4080
Radeon Instinct MI300
Architecture
Ada Lovelace
CDNA 3.0
GPU code name
AD103-300-A1
Aqua Vanjaram
Market segment
Desktop
Desktop
Release date
September 2022
January 2023
Interface
PCIe 4.0 x16
PCIe 5.0 x16
Supplementary power connectors
1x 16-pin
2x 8-pin
Boost clock speed
2505 MHz
1700 MHz
Core clock speed
2205 MHz
-
Manufacturing process technology
5 nm
5 nm
Number of transistors
45,900 million
153,000 million
Pipelines / CUDA cores
9728
14080
Power consumption (TDP)
320 Watt
600 Watt
Texture fill rate
761.5
1,496
Memory type
GDDR6X
HBM3
Maximum RAM amount
16 GB
128 GB
Memory bus width
256 Bit
8192 Bit
Memory clock speed
22400 MHz
3.2 GB/s
Memory bandwidth
716.8 GB/s
3,277 GB/s
Shared memory
-
-
Display Connectors
1x HDMI 2.1, 3x DisplayPort 1.4a
No outputs
HDMI
+
-
DirectX
12 Ultimate (12_2)
N/A
CUDA
8.9
-
OpenCL
3.0
3.0
OpenGL
4.6
N/A
Shader Model
6.6
N/A
Vulkan
1.3
N/A