NVIDIA GeForce RTX 4070 vs AMD Radeon RX 8800 XT
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 4070 and 16GB VRAM Radeon RX 8800 XT to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 4070 's Advantages
Boost Clock has increased by 2% (2475MHz vs 2430MHz)
1792 additional rendering cores
Lower TDP (200W vs 220W)
AMD Radeon RX 8800 XT 's Advantages
More VRAM (16GB vs 12GB)
Larger VRAM bandwidth (624.1GB/s vs 504.2GB/s)
Score
Benchmark
FP32 (float)
GeForce RTX 4070
+46%
29.15 TFLOPS
Radeon RX 8800 XT
19.91 TFLOPS
Graphics Card
Apr 2023
Release Date
Unknown
GeForce 40
Generation
Navi IV(RX 8000)
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1920 MHz
Base Clock
1295 MHz
2475 MHz
Boost Clock
2430 MHz
1313 MHz
Memory Clock
2438 MHz
Memory
12GB
Memory Size
16GB
GDDR6X
Memory Type
GDDR6
192bit
Memory Bus
256bit
504.2GB/s
Bandwidth
624.1GB/s
Render Config
-
Compute Units
64
46
SM Count
-
5888
Shading Units
4096
184
TMUs
256
64
ROPs
96
184
Tensor Cores
-
46
RT Cores
64
128 KB (per SM)
L1 Cache
128 KB per Array
36 MB
L2 Cache
4 MB
-
L3 Cache
64 MB
Theoretical Performance
158.4 GPixel/s
Pixel Rate
233.3 GPixel/s
455.4 GTexel/s
Texture Rate
622.1 GTexel/s
29.15 TFLOPS
FP16 (half)
39.81 TFLOPS
29.15 TFLOPS
FP32 (float)
19.91 TFLOPS
455.4 GFLOPS
FP64 (double)
622.1 GFLOPS
Board Design
200W
TDP
220W
550 W
Suggested PSU
550 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1a3x DisplayPort 2.1
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
AD104
GPU Name
Navi 48
AD104-250-A1
GPU Variant
Navi 48 XT
Ada Lovelace
Architecture
RDNA 4.0
TSMC
Foundry
TSMC
5 nm
Process Size
4 nm
35.8 billion
Transistors
Unknown
295 mm²
Die Size
Unknown
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
6.8
