GeForce RTX 4060 vs GeForce RTX 5090
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 4060 and 32GB VRAM GeForce RTX 5090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 4060 's Advantages
Boost Clock has increased by 2% (2460MHz vs 2407MHz)
Lower TDP (115W vs 575W)
GeForce RTX 5090 's Advantages
Released 1 years and 8 months late
More VRAM (32GB vs 8GB)
Larger VRAM bandwidth (1.79TB/s vs 272.0GB/s)
18688 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 4060
15110
GeForce RTX 5090
+593%
104800
3DMark Time Spy
GeForce RTX 4060
10615
GeForce RTX 5090
+347%
47510
3DMark Time Spy Extreme
GeForce RTX 4060
4959
GeForce RTX 5090
+420%
25825
3DMark Speed Way
GeForce RTX 4060
2646
GeForce RTX 5090
+452%
14621
Graphics Card
May 2023
Release Date
Jan 2025
GeForce 40
Generation
GeForce 50
Desktop
Type
Desktop
PCIe 4.0 x8
Bus Interface
PCIe 5.0 x16
Clock Speeds
1830 MHz
Base Clock
2017 MHz
2460 MHz
Boost Clock
2407 MHz
2125 MHz
Memory Clock
1750 MHz
Memory
8GB
Memory Size
32GB
GDDR6
Memory Type
GDDR7
128bit
Memory Bus
512bit
272.0GB/s
Bandwidth
1.79TB/s
Render Config
24
SM Count
170
3072
Shading Units
21760
96
TMUs
680
48
ROPs
176
96
Tensor Cores
680
24
RT Cores
170
128 KB (per SM)
L1 Cache
128 KB (per SM)
24 MB
L2 Cache
96 MB
Theoretical Performance
118.1 GPixel/s
Pixel Rate
423.6 GPixel/s
236.2 GTexel/s
Texture Rate
1637 GTexel/s
15.11 TFLOPS
FP16 (half)
104.8 TFLOPS
15.11 TFLOPS
FP32 (float)
104.8 TFLOPS
236.2 GFLOPS
FP64 (double)
1.637 TFLOPS
Board Design
115W
TDP
575W
300 W
Suggested PSU
950 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1b
1x 12-pin
Power Connectors
1x 16-pin
Graphics Processor
AD107
GPU Name
GB202
AD107-400-A1
GPU Variant
GB202-300-A1
Ada Lovelace
Architecture
Blackwell 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
18.9 billion
Transistors
92.2 billion
159 mm²
Die Size
750 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.4
8.9
CUDA
12.0
6.7
Shader Model
6.8
