GeForce RTX 3090 Ti vs Radeon R9 FURY
We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 3090 Ti and 4GB VRAM Radeon R9 FURY to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3090 Ti 's Advantages
Released 6 years and 6 months late
Boost Clock1860MHz
More VRAM (24GB vs 4GB)
Larger VRAM bandwidth (1008GB/s vs 512.0GB/s)
7168 additional rendering cores
Radeon R9 FURY 's Advantages
Lower TDP (275W vs 450W)
Score
Benchmark
FP32 (float)
GeForce RTX 3090 Ti
+458%
40000
Radeon R9 FURY
7168
3DMark Time Spy
GeForce RTX 3090 Ti
+349%
21832
Radeon R9 FURY
4858
3DMark Time Spy Extreme
GeForce RTX 3090 Ti
+397%
11318
Radeon R9 FURY
2277
Shadow of the Tomb Raider 2160p
GeForce RTX 3090 Ti
+320%
105
Radeon R9 FURY
25
Shadow of the Tomb Raider 1440p
GeForce RTX 3090 Ti
+203%
167
Radeon R9 FURY
55
Shadow of the Tomb Raider 1080p
GeForce RTX 3090 Ti
+200%
210
Radeon R9 FURY
70
GTA 5 2160p
GeForce RTX 3090 Ti
+220%
141
Radeon R9 FURY
44
GTA 5 1440p
GeForce RTX 3090 Ti
+259%
187
Radeon R9 FURY
52
GTA 5 1080p
GeForce RTX 3090 Ti
+56%
226
Radeon R9 FURY
144
Graphics Card
Jan 2022
Release Date
Jul 2015
GeForce 30
Generation
Pirate Islands
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1560 MHz
Base Clock
-
1860 MHz
Boost Clock
-
1313 MHz
Memory Clock
500 MHz
Memory
24GB
Memory Size
4GB
GDDR6X
Memory Type
HBM
384bit
Memory Bus
4096bit
1008GB/s
Bandwidth
512.0GB/s
Render Config
-
Compute Units
56
84
SM Count
-
10752
Shading Units
3584
336
TMUs
224
112
ROPs
64
336
Tensor Cores
-
84
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
6 MB
L2 Cache
2 MB
Theoretical Performance
208.3 GPixel/s
Pixel Rate
64.00 GPixel/s
625.0 GTexel/s
Texture Rate
224.0 GTexel/s
40.00 TFLOPS
FP16 (half)
7.168 TFLOPS
40.00 TFLOPS
FP32 (float)
7.168 TFLOPS
625.0 GFLOPS
FP64 (double)
448.0 GFLOPS
Board Design
450W
TDP
275W
850 W
Suggested PSU
600 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 1.4a
3x DisplayPort 1.2
1x 16-pin
Power Connectors
2x 8-pin
Graphics Processor
GA102
GPU Name
Fiji
GA102-350-A1
GPU Variant
Fiji PRO CB
(215-0862046)
Ampere
Architecture
GCN 3.0
Samsung
Foundry
TSMC
8 nm
Process Size
28 nm
28.3 billion
Transistors
8.9 billion
628 mm²
Die Size
596 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.0
1.3
Vulkan
1.2
8.6
CUDA
-
6.6
Shader Model
6.3