GeForce GTX 970 vs Radeon RX 470
We compared two Desktop platform GPUs: 4GB VRAM GeForce GTX 970 and 4GB VRAM Radeon RX 470 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce GTX 970 's Advantages
Larger VRAM bandwidth (224.4GB/s vs 211.2GB/s)
Radeon RX 470 's Advantages
Released 1 years and 11 months late
Boost Clock has increased by 2% (1206MHz vs 1178MHz)
384 additional rendering cores
Lower TDP (120W vs 148W)
Score
Benchmark
FP32 (float)
GeForce GTX 970
3920
Radeon RX 470
+26%
4940
3DMark Time Spy
GeForce GTX 970
3646
Radeon RX 470
3679
3DMark Time Spy Extreme
GeForce GTX 970
1683
Radeon RX 470
+1%
1701
Shadow of the Tomb Raider 2160p
GeForce GTX 970
+25%
15
Radeon RX 470
12
Shadow of the Tomb Raider 1440p
GeForce GTX 970
+20%
30
Radeon RX 470
25
Shadow of the Tomb Raider 1080p
GeForce GTX 970
40
Radeon RX 470
40
GTA 5 1440p
GeForce GTX 970
+29%
44
Radeon RX 470
34
GTA 5 1080p
GeForce GTX 970
98
Radeon RX 470
98
Graphics Card
Sep 2014
Release Date
Aug 2016
GeForce 900
Generation
Arctic Islands
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1050 MHz
Base Clock
926 MHz
1178 MHz
Boost Clock
1206 MHz
1753 MHz
Memory Clock
1650 MHz
Memory
4GB
Memory Size
4GB
GDDR5
Memory Type
GDDR5
256bit
Memory Bus
256bit
224.4GB/s
Bandwidth
211.2GB/s
Render Config
-
Compute Units
32
1664
Shading Units
2048
104
TMUs
128
56
ROPs
32
48 KB (per SMM)
L1 Cache
16 KB (per CU)
2 MB
L2 Cache
2 MB
Theoretical Performance
65.97 GPixel/s
Pixel Rate
38.59 GPixel/s
122.5 GTexel/s
Texture Rate
154.4 GTexel/s
-
FP16 (half)
4.940 TFLOPS
3.920 TFLOPS
FP32 (float)
4.940 TFLOPS
122.5 GFLOPS
FP64 (double)
308.7 GFLOPS
Board Design
148W
TDP
120W
300 W
Suggested PSU
300 W
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a
Outputs
1x HDMI 2.0b
3x DisplayPort 1.4a
2x 6-pin
Power Connectors
1x 6-pin
Graphics Processor
GM204
GPU Name
Ellesmere
GM204-200-A1
GPU Variant
Polaris 10 PRO
(215-0876204)
Maxwell 2.0
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
28 nm
Process Size
14 nm
5.2 billion
Transistors
5.7 billion
398 mm²
Die Size
232 mm²
Graphics Features
12 (12_1)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
5.2
CUDA
-
6.4
Shader Model
6.4