GeForce RTX 3070 vs Radeon RX 9070 XT
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3070 and 16GB VRAM Radeon RX 9070 XT to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3070 's Advantages
1792 additional rendering cores
Lower TDP (220W vs 304W)
Radeon RX 9070 XT 's Advantages
Released 4 years and 6 months late
Boost Clock has increased by 72% (2970MHz vs 1725MHz)
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (644.6GB/s vs 448.0GB/s)
Score
Benchmark
FP32 (float)
GeForce RTX 3070
20310
Radeon RX 9070 XT
+139%
48660
3DMark Time Spy
GeForce RTX 3070
13641
Radeon RX 9070 XT
+123%
30445
3DMark Time Spy Extreme
GeForce RTX 3070
6762
Radeon RX 9070 XT
+116%
14633
3DMark Speed Way
GeForce RTX 3070
3453
Radeon RX 9070 XT
+85%
6403
Graphics Card
Sep 2020
Release Date
Mar 2025
GeForce 30
Generation
Navi IV
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1500 MHz
Base Clock
1660 MHz
1725 MHz
Boost Clock
2970 MHz
1750 MHz
Memory Clock
2518 MHz
Memory
8GB
Memory Size
16GB
GDDR6
Memory Type
GDDR6
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
644.6GB/s
Render Config
-
Compute Units
64
46
SM Count
-
5888
Shading Units
4096
184
TMUs
256
96
ROPs
128
184
Tensor Cores
128
46
RT Cores
64
128 KB (per SM)
L1 Cache
128 KB per Array
4 MB
L2 Cache
8 MB
-
L3 Cache
64 MB
Theoretical Performance
165.6 GPixel/s
Pixel Rate
380.2 GPixel/s
317.4 GTexel/s
Texture Rate
760.3 GTexel/s
20.31 TFLOPS
FP16 (half)
97.32 TFLOPS
20.31 TFLOPS
FP32 (float)
48.66 TFLOPS
317.4 GFLOPS
FP64 (double)
1.521 TFLOPS
Board Design
220W
TDP
304W
550 W
Suggested PSU
700 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1a
1x 12-pin
Power Connectors
2x 8-pin
Graphics Processor
GA104
GPU Name
Navi 48
GA104-300-A1
GPU Variant
Navi 48 XT
(215-176600315)
Ampere
Architecture
RDNA 4.0
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
17.4 billion
Transistors
53.9 billion
392 mm²
Die Size
357 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
-
6.6
Shader Model
6.8