Radeon RX 6400 vs GeForce RTX 5090
We compared two Desktop platform GPUs: 4GB VRAM Radeon RX 6400 and 32GB VRAM GeForce RTX 5090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon RX 6400 's Advantages
Lower TDP (53W vs 575W)
GeForce RTX 5090 's Advantages
Released 3 years late
Boost Clock has increased by 4% (2407MHz vs 2321MHz)
More VRAM (32GB vs 4GB)
Larger VRAM bandwidth (1.79TB/s vs 128.0GB/s)
20992 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon RX 6400
3565
GeForce RTX 5090
+2839%
104800
3DMark Time Spy
Radeon RX 6400
3585
GeForce RTX 5090
+1225%
47510
3DMark Time Spy Extreme
Radeon RX 6400
1662
GeForce RTX 5090
+1453%
25825
3DMark Speed Way
Radeon RX 6400
103
GeForce RTX 5090
+14095%
14621
Graphics Card
Jan 2022
Release Date
Jan 2025
Navi II
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 4.0 x4
Bus Interface
PCIe 5.0 x16
Clock Speeds
1923 MHz
Base Clock
2017 MHz
2321 MHz
Boost Clock
2407 MHz
2000 MHz
Memory Clock
1750 MHz
Memory
4GB
Memory Size
32GB
GDDR6
Memory Type
GDDR7
64bit
Memory Bus
512bit
128.0GB/s
Bandwidth
1.79TB/s
Render Config
12
Compute Units
-
-
SM Count
170
768
Shading Units
21760
48
TMUs
680
32
ROPs
176
-
Tensor Cores
680
12
RT Cores
170
128 KB per Array
L1 Cache
128 KB (per SM)
1024 KB
L2 Cache
96 MB
16 MB
L3 Cache
-
Theoretical Performance
74.27 GPixel/s
Pixel Rate
423.6 GPixel/s
111.4 GTexel/s
Texture Rate
1637 GTexel/s
7.130 TFLOPS
FP16 (half)
104.8 TFLOPS
3.565 TFLOPS
FP32 (float)
104.8 TFLOPS
222.8 GFLOPS
FP64 (double)
1.637 TFLOPS
Board Design
53W
TDP
575W
250 W
Suggested PSU
950 W
1x HDMI 2.1
1x DisplayPort 1.4a
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1b
None
Power Connectors
1x 16-pin
Graphics Processor
Navi 24
GPU Name
GB202
Navi 24 XL
(215-135000046)
GPU Variant
GB202-300-A1
RDNA 2.0
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
6 nm
Process Size
5 nm
5.4 billion
Transistors
92.2 billion
107 mm²
Die Size
750 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.2
OpenCL
3.0
1.3
Vulkan
1.4
-
CUDA
12.0
6.7
Shader Model
6.8