NVIDIA GeForce RTX 5080 vs AMD Radeon R9 390X

GPU · Specs Compare

Products
GPU NVIDIA GeForce RTX 5080 NVIDIA · 2025-01
GPU AMD Radeon R9 390X AMD · 2015-06
Graphics Card
Release Date
Jan 2025
Jun 2015
Generation
GeForce 50
Pirate Islands
Type
Desktop
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
2295 MHz
—
Boost Clock
2617 MHz
—
Memory Clock
1875 MHz
1500 MHz
Memory
Memory Size
16GB
8GB
Memory Type
GDDR7
GDDR5
Memory Bus
256bit
512bit
Bandwidth
960.0GB/s
384.0GB/s
Render Config
SM Count
84
—
Shading Units
10752
2816
TMUs
336
176
ROPs
112
64
Tensor Cores
336
—
RT Cores
84
—
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
64 MB
1024 KB
Compute Units
—
44
Theoretical Performance
Pixel Rate
293.1 GPixel/s
67.20 GPixel/s
Texture Rate
879.3 GTexel/s
184.8 GTexel/s
FP16 (half)
56.28 TFLOPS
—
FP32 (float)
56.28 TFLOPS
5.914 TFLOPS
FP64 (double)
879.3 GFLOPS
739.2 GFLOPS
Graphics Processor
GPU Name
GB203
Grenada
GPU Variant
GB203-400-A1
Grenada XT(215-0880004)
Architecture
Blackwell 2.0
GCN 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
28 nm
Transistors
45.6 billion
6.2 billion
Die Size
378 mm²
438 mm²
Board Design
TDP
360W
275W
Suggested PSU
750 W
600 W
Outputs
1x HDMI 2.1b3x DisplayPort 2.1b
2x DVI1x HDMI 1.4a1x DisplayPort 1.2
Power Connectors
1x 16-pin
1x 6-pin + 1x 8-pin
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
OpenCL
3.0
2.0
Vulkan
1.4
1.2
CUDA
12.0
—
Shader Model
6.8
6.3
Benchmark
3DMark Time Spy
33,116
—
3DMark Time Spy Extreme
16,627
—
3DMark Speed Way
9,296
—
▲ Specs Compare Data sourced from official specifications and benchmark tests.