NVIDIA GeForce RTX 3060 Ti GDDR6X vs AMD Radeon Pro W6400
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3060 Ti GDDR6X and 4GB VRAM Radeon Pro W6400 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 3060 Ti GDDR6X 's Advantages
Released 9 months late
More VRAM (8GB vs 4GB)
Larger VRAM bandwidth (608.3GB/s vs 112.0GB/s)
4096 additional rendering cores
AMD Radeon Pro W6400 's Advantages
Boost Clock has increased by 40% (2331MHz vs 1665MHz)
Lower TDP (50W vs 225W)
Score
Benchmark
FP32 (float)
GeForce RTX 3060 Ti GDDR6X
+352%
16.2 TFLOPS
Radeon Pro W6400
3.58 TFLOPS
3DMark Time Spy
GeForce RTX 3060 Ti GDDR6X
+239%
12223
Radeon Pro W6400
3604
3DMark Time Spy Extreme
GeForce RTX 3060 Ti GDDR6X
+261%
5941
Radeon Pro W6400
1644
3DMark Speed Way
GeForce RTX 3060 Ti GDDR6X
+1583%
3097
Radeon Pro W6400
184
Shadow of the Tomb Raider 2160p
GeForce RTX 3060 Ti GDDR6X
+525%
50
Radeon Pro W6400
8
Shadow of the Tomb Raider 1440p
GeForce RTX 3060 Ti GDDR6X
+350%
90
Radeon Pro W6400
20
Shadow of the Tomb Raider 1080p
GeForce RTX 3060 Ti GDDR6X
+294%
138
Radeon Pro W6400
35
Graphics Card
Oct 2022
Release Date
Jan 2022
GeForce 30
Generation
Radeon Pro
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x4
Clock Speeds
1410 MHz
Base Clock
2331 MHz
1665 MHz
Boost Clock
2331 MHz
1188 MHz
Memory Clock
1750 MHz
Memory
8GB
Memory Size
4GB
GDDR6X
Memory Type
GDDR6
256bit
Memory Bus
64bit
608.3GB/s
Bandwidth
112.0GB/s
Render Config
-
Compute Units
12
38
SM Count
-
4864
Shading Units
768
152
TMUs
48
80
ROPs
32
152
Tensor Cores
-
38
RT Cores
12
128 KB (per SM)
L1 Cache
128 KB per Array
4 MB
L2 Cache
1024 KB
-
L3 Cache
8 MB
Theoretical Performance
133.2 GPixel/s
Pixel Rate
74.59 GPixel/s
253.1 GTexel/s
Texture Rate
111.9 GTexel/s
16.20 TFLOPS
FP16 (half)
7.161 TFLOPS
16.20 TFLOPS
FP32 (float)
3.580 TFLOPS
253.1 GFLOPS
FP64 (double)
223.8 GFLOPS
Board Design
225W
TDP
50W
550 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
2x DisplayPort 1.4a
1x 12-pin
Power Connectors
None
Graphics Processor
GA104
GPU Name
Navi 24
GA104-202-A1
GPU Variant
Navi 24 XL-W
Ampere
Architecture
RDNA 2.0
Samsung
Foundry
TSMC
8 nm
Process Size
6 nm
17.4 billion
Transistors
5.4 billion
392 mm²
Die Size
107 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
2.2
1.3
Vulkan
1.3
8.6
CUDA
-
6.7
Shader Model
6.6
