Radeon RX 470 vs GeForce GTX 1650 GDDR6
We compared two Desktop platform GPUs: 4GB VRAM Radeon RX 470 and 4GB VRAM GeForce GTX 1650 GDDR6 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon RX 470 's Advantages
Larger VRAM bandwidth (211.2GB/s vs 192.0GB/s)
1152 additional rendering cores
GeForce GTX 1650 GDDR6 's Advantages
Released 3 years and 8 months late
Boost Clock has increased by 32% (1590MHz vs 1206MHz)
Lower TDP (75W vs 120W)
Score
Benchmark
FP32 (float)
Radeon RX 470
+73%
4940
GeForce GTX 1650 GDDR6
2849
3DMark Time Spy
Radeon RX 470
+3%
3679
GeForce GTX 1650 GDDR6
3566
3DMark Time Spy Extreme
Radeon RX 470
+5%
1701
GeForce GTX 1650 GDDR6
1607
Shadow of the Tomb Raider 2160p
Radeon RX 470
12
GeForce GTX 1650 GDDR6
+16%
14
Shadow of the Tomb Raider 1440p
Radeon RX 470
25
GeForce GTX 1650 GDDR6
+16%
29
Shadow of the Tomb Raider 1080p
Radeon RX 470
40
GeForce GTX 1650 GDDR6
+10%
44
GTA 5 1440p
Radeon RX 470
+13%
34
GeForce GTX 1650 GDDR6
30
GTA 5 1080p
Radeon RX 470
98
GeForce GTX 1650 GDDR6
+2%
100
Graphics Card
Aug 2016
Release Date
Apr 2020
Arctic Islands
Generation
GeForce 16
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
926 MHz
Base Clock
1410 MHz
1206 MHz
Boost Clock
1590 MHz
1650 MHz
Memory Clock
1500 MHz
Memory
4GB
Memory Size
4GB
GDDR5
Memory Type
GDDR6
256bit
Memory Bus
128bit
211.2GB/s
Bandwidth
192.0GB/s
Render Config
32
Compute Units
-
-
SM Count
14
2048
Shading Units
896
128
TMUs
56
32
ROPs
32
16 KB (per CU)
L1 Cache
64 KB (per SM)
2 MB
L2 Cache
1024 KB
Theoretical Performance
38.59 GPixel/s
Pixel Rate
50.88 GPixel/s
154.4 GTexel/s
Texture Rate
89.04 GTexel/s
4.940 TFLOPS
FP16 (half)
5.699 TFLOPS
4.940 TFLOPS
FP32 (float)
2.849 TFLOPS
308.7 GFLOPS
FP64 (double)
89.04 GFLOPS
Board Design
120W
TDP
75W
300 W
Suggested PSU
250 W
1x HDMI 2.0b
3x DisplayPort 1.4a
Outputs
1x DVI
1x HDMI 2.0
1x DisplayPort 1.4a
1x 6-pin
Power Connectors
None
Graphics Processor
Ellesmere
GPU Name
TU117
Polaris 10 PRO
(215-0876204)
GPU Variant
TU117-300-A1
GCN 4.0
Architecture
Turing
GlobalFoundries
Foundry
TSMC
14 nm
Process Size
12 nm
5.7 billion
Transistors
4.7 billion
232 mm²
Die Size
200 mm²
Graphics Features
12 (12_0)
DirectX
12 (12_1)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.2
Vulkan
1.3
-
CUDA
7.5
6.4
Shader Model
6.6