Radeon RX 6600 XT vs GeForce RTX 3070
We compared two Desktop platform GPUs: 8GB VRAM Radeon RX 6600 XT and 8GB VRAM GeForce RTX 3070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Radeon RX 6600 XT 's Advantages
Released 10 months late
Boost Clock has increased by 50% (2589MHz vs 1725MHz)
Lower TDP (160W vs 220W)
GeForce RTX 3070 's Advantages
Larger VRAM bandwidth (448.0GB/s vs 256.0GB/s)
3840 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon RX 6600 XT
10600
GeForce RTX 3070
+91%
20310
3DMark Time Spy
Radeon RX 6600 XT
9656
GeForce RTX 3070
+41%
13641
3DMark Time Spy Extreme
Radeon RX 6600 XT
4399
GeForce RTX 3070
+53%
6762
3DMark Speed Way
Radeon RX 6600 XT
1675
GeForce RTX 3070
+106%
3453
Shadow of the Tomb Raider 2160p
Radeon RX 6600 XT
38
GeForce RTX 3070
+39%
53
Shadow of the Tomb Raider 1440p
Radeon RX 6600 XT
72
GeForce RTX 3070
+31%
95
Shadow of the Tomb Raider 1080p
Radeon RX 6600 XT
119
GeForce RTX 3070
+21%
144
Cyberpunk 2077 2160p
Radeon RX 6600 XT
29
GeForce RTX 3070
+58%
46
Cyberpunk 2077 1440p
Radeon RX 6600 XT
36
GeForce RTX 3070
+55%
56
Cyberpunk 2077 1080p
Radeon RX 6600 XT
58
GeForce RTX 3070
+41%
82
Battlefield 5 2160p
Radeon RX 6600 XT
58
GeForce RTX 3070
+39%
81
Battlefield 5 1440p
Radeon RX 6600 XT
111
GeForce RTX 3070
+27%
141
Battlefield 5 1080p
Radeon RX 6600 XT
144
GeForce RTX 3070
+30%
188
GTA 5 2160p
Radeon RX 6600 XT
61
GeForce RTX 3070
+11%
68
GTA 5 1440p
Radeon RX 6600 XT
82
GeForce RTX 3070
+28%
105
GTA 5 1080p
Radeon RX 6600 XT
149
GeForce RTX 3070
+6%
159
Horizon Forbidden West 1080p
Radeon RX 6600 XT
64
GeForce RTX 3070
+28%
82
Horizon Forbidden West 1440p
Radeon RX 6600 XT
48
GeForce RTX 3070
+27%
61
Horizon Forbidden West 2160p
Radeon RX 6600 XT
26
GeForce RTX 3070
+50%
39
Graphics Card
Jul 2021
Release Date
Sep 2020
Navi II
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x8
Bus Interface
PCIe 4.0 x16
Clock Speeds
1968 MHz
Base Clock
1500 MHz
2589 MHz
Boost Clock
1725 MHz
2000 MHz
Memory Clock
1750 MHz
Memory
8GB
Memory Size
8GB
GDDR6
Memory Type
GDDR6
128bit
Memory Bus
256bit
256.0GB/s
Bandwidth
448.0GB/s
Render Config
32
Compute Units
-
-
SM Count
46
2048
Shading Units
5888
128
TMUs
184
64
ROPs
96
-
Tensor Cores
184
32
RT Cores
46
128 KB per Array
L1 Cache
128 KB (per SM)
2 MB
L2 Cache
4 MB
32 MB
L3 Cache
-
Theoretical Performance
165.7 GPixel/s
Pixel Rate
165.6 GPixel/s
331.4 GTexel/s
Texture Rate
317.4 GTexel/s
21.21 TFLOPS
FP16 (half)
20.31 TFLOPS
10.60 TFLOPS
FP32 (float)
20.31 TFLOPS
662.8 GFLOPS
FP64 (double)
317.4 GFLOPS
Board Design
160W
TDP
220W
450 W
Suggested PSU
550 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 12-pin
Graphics Processor
Navi 23
GPU Name
GA104
Navi 23 XT
(215-130000006)
GPU Variant
GA104-300-A1
RDNA 2.0
Architecture
Ampere
TSMC
Foundry
Samsung
7 nm
Process Size
8 nm
11.06 billion
Transistors
17.4 billion
237 mm²
Die Size
392 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.3
Vulkan
1.3
-
CUDA
8.6
6.7
Shader Model
6.6
