AMD Radeon AI PRO 9600D vs NVIDIA GeForce RTX 3080
GPU · Specs Compare
Graphics Card
Release Date
Dec 2025
Sep 2020
Generation
Radeon Pro Navi
GeForce 30
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
1080 MHz
1440 MHz
Boost Clock
2020 MHz
1710 MHz
Memory Clock
2250 MHz
1188 MHz
Memory
Memory Size
32GB
10GB
Memory Type
GDDR6
GDDR6X
Memory Bus
256bit
320bit
Bandwidth
576.0GB/s
760.3GB/s
Render Config
Compute Units
48
—
Shading Units
3072
8704
TMUs
192
272
ROPs
96
96
RT Cores
48
68
L2 Cache
8 MB
5 MB
L3 Cache
48 MB
—
SM Count
—
68
Tensor Cores
—
272
L1 Cache
—
128 KB (per SM)
Theoretical Performance
Pixel Rate
193.9 GPixel/s
164.2 GPixel/s
Texture Rate
387.8 GTexel/s
465.1 GTexel/s
FP16 (half)
49.64 TFLOPS
29.77 TFLOPS
FP32 (float)
24.82 TFLOPS
29.77 TFLOPS
FP64 (double)
775.7 GFLOPS
465.1 GFLOPS
Graphics Processor
GPU Name
Navi 48
GA102
GPU Variant
Navi 48 XLW
GA102-200-KD-A1
Architecture
RDNA 4.0
Ampere
Foundry
TSMC
Samsung
Process Size
4 nm
8 nm
Transistors
53.9 billion
28.3 billion
Die Size
357 mm²
628 mm²
Board Design
TDP
150W
320W
Suggested PSU
450 W
700 W
Outputs
1x DisplayPort 2.1a
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
1x 16-pin
1x 12-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
2.2
3.0
Vulkan
1.4
1.3
Shader Model
6.8
6.6
CUDA
—
8.6
Benchmark
3DMark Time Spy
—
17,662
3DMark Time Spy Extreme
—
8,879
▲ Specs Compare
Data sourced from official specifications and benchmark tests.