GeForce RTX 4070 vs Radeon RX 6400
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 and 4GB VRAM Radeon RX 6400 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 4070 Advantages
Released 1 years and 3 months late
Boost Clock has increased by 7% (2475MHz vs 2321MHz)
More VRAM (12GB vs 4GB)
Larger VRAM bandwidth (504.2GB/s vs 128.0GB/s)
5120 additional rendering cores
Radeon RX 6400 Advantages
Lower TDP (53W vs 200W)
Score
Benchmark
FP32 (float)
GeForce RTX 4070
+717%
29150
Radeon RX 6400
3565
3DMark Time Spy
GeForce RTX 4070
+398%
17887
Radeon RX 6400
3585
3DMark Time Spy Extreme
GeForce RTX 4070
+375%
7907
Radeon RX 6400
1662
3DMark Speed Way
GeForce RTX 4070
+5247%
5508
Radeon RX 6400
103
Blender
GeForce RTX 4070
+1641%
5818
Radeon RX 6400
334
Shadow of the Tomb Raider 2160p
GeForce RTX 4070
+925%
82
Radeon RX 6400
8
Shadow of the Tomb Raider 1440p
GeForce RTX 4070
+700%
160
Radeon RX 6400
20
Shadow of the Tomb Raider 1080p
GeForce RTX 4070
+631%
256
Radeon RX 6400
35
Cyberpunk 2077 2160p
GeForce RTX 4070
+575%
54
Radeon RX 6400
8
Cyberpunk 2077 1440p
GeForce RTX 4070
+745%
93
Radeon RX 6400
11
Cyberpunk 2077 1080p
GeForce RTX 4070
+519%
130
Radeon RX 6400
21
Battlefield 5 2160p
GeForce RTX 4070
+415%
98
Radeon RX 6400
19
Battlefield 5 1440p
GeForce RTX 4070
+377%
172
Radeon RX 6400
36
Battlefield 5 1080p
GeForce RTX 4070
+316%
200
Radeon RX 6400
48
Graphics Card
Apr 2023
Release Date
Jan 2022
GeForce 40
Generation
Navi II
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x4
Clock Speeds
1920 MHz
Base Clock
1923 MHz
2475 MHz
Boost Clock
2321 MHz
1313 MHz
Memory Clock
2000 MHz
Memory
12GB
Memory Size
4GB
GDDR6X
Memory Type
GDDR6
192bit
Memory Bus
64bit
504.2GB/s
Bandwidth
128.0GB/s
Render Config
-
Compute Units
12
46
SM Count
-
5888
Shading Units
768
184
TMUs
48
64
ROPs
32
184
Tensor Cores
-
46
RT Cores
12
128 KB (per SM)
L1 Cache
128 KB per Array
36 MB
L2 Cache
1024 KB
-
L3 Cache
16 MB
Theoretical Performance
158.4 GPixel/s
Pixel Rate
74.27 GPixel/s
455.4 GTexel/s
Texture Rate
111.4 GTexel/s
29.15 TFLOPS
FP16 (half)
7.130 TFLOPS
29.15 TFLOPS
FP32 (float)
3.565 TFLOPS
455.4 GFLOPS
FP64 (double)
222.8 GFLOPS
Board Design
200W
TDP
53W
550 W
Suggested PSU
250 W
1x HDMI 2.1
3x DisplayPort 1.4a
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
1x DisplayPort 1.4a
1x DisplayPort 1.4a
1x 16-pin
Power Connectors
None
Graphics Processor
AD104
GPU Name
Navi 24
AD104-250-A1
GPU Variant
Navi 24 XL
(215-135000046)
(215-135000046)
Ada Lovelace
Architecture
RDNA 2.0
TSMC
Foundry
TSMC
5 nm
Process Size
6 nm
35.8 billion
Transistors
5.4 billion
295 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
8.9
CUDA
-
6.7
Shader Model
6.7