GeForce RTX 3070 vs GeForce RTX 3070 Ti
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3070 and 8GB VRAM GeForce RTX 3070 Ti to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3070 's Advantages
Lower TDP (220W vs 290W)
GeForce RTX 3070 Ti 's Advantages
Released 8 months late
Boost Clock has increased by 3% (1770MHz vs 1725MHz)
Larger VRAM bandwidth (608.3GB/s vs 448.0GB/s)
256 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3070
20310
GeForce RTX 3070 Ti
+7%
21750
3DMark Time Spy
GeForce RTX 3070
13641
GeForce RTX 3070 Ti
+9%
14872
3DMark Time Spy Extreme
GeForce RTX 3070
6762
GeForce RTX 3070 Ti
+9%
7416
3DMark Speed Way
GeForce RTX 3070
3453
GeForce RTX 3070 Ti
+8%
3761
Shadow of the Tomb Raider 2160p
GeForce RTX 3070
53
GeForce RTX 3070 Ti
+32%
70
Shadow of the Tomb Raider 1440p
GeForce RTX 3070
95
GeForce RTX 3070 Ti
+31%
125
Shadow of the Tomb Raider 1080p
GeForce RTX 3070
144
GeForce RTX 3070 Ti
+23%
178
Cyberpunk 2077 2160p
GeForce RTX 3070
46
GeForce RTX 3070 Ti
+15%
53
Cyberpunk 2077 1440p
GeForce RTX 3070
56
GeForce RTX 3070 Ti
+16%
65
Cyberpunk 2077 1080p
GeForce RTX 3070
82
GeForce RTX 3070 Ti
+17%
96
Battlefield 5 2160p
GeForce RTX 3070
81
GeForce RTX 3070 Ti
+4%
85
Battlefield 5 1440p
GeForce RTX 3070
141
GeForce RTX 3070 Ti
+3%
146
Battlefield 5 1080p
GeForce RTX 3070
188
GeForce RTX 3070 Ti
188
GTA 5 2160p
GeForce RTX 3070
68
GeForce RTX 3070 Ti
+11%
76
GTA 5 1440p
GeForce RTX 3070
105
GeForce RTX 3070 Ti
+8%
114
GTA 5 1080p
GeForce RTX 3070
159
GeForce RTX 3070 Ti
+3%
164
Horizon Forbidden West 1080p
GeForce RTX 3070
82
GeForce RTX 3070 Ti
+2%
84
Horizon Forbidden West 1440p
GeForce RTX 3070
61
GeForce RTX 3070 Ti
+4%
64
Horizon Forbidden West 2160p
GeForce RTX 3070
39
GeForce RTX 3070 Ti
+7%
42
Graphics Card
Sep 2020
Release Date
May 2021
GeForce 30
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1500 MHz
Base Clock
1575 MHz
1725 MHz
Boost Clock
1770 MHz
1750 MHz
Memory Clock
1188 MHz
Memory
8GB
Memory Size
8GB
GDDR6
Memory Type
GDDR6X
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
608.3GB/s
Render Config
46
SM Count
48
5888
Shading Units
6144
184
TMUs
192
96
ROPs
96
184
Tensor Cores
192
46
RT Cores
48
128 KB (per SM)
L1 Cache
128 KB (per SM)
4 MB
L2 Cache
4 MB
Theoretical Performance
165.6 GPixel/s
Pixel Rate
169.9 GPixel/s
317.4 GTexel/s
Texture Rate
339.8 GTexel/s
20.31 TFLOPS
FP16 (half)
21.75 TFLOPS
20.31 TFLOPS
FP32 (float)
21.75 TFLOPS
317.4 GFLOPS
FP64 (double)
339.8 GFLOPS
Board Design
220W
TDP
290W
550 W
Suggested PSU
600 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 12-pin
Power Connectors
1x 12-pin
Graphics Processor
GA104
GPU Name
GA104
GA104-300-A1
GPU Variant
GA104-400-A1
Ampere
Architecture
Ampere
Samsung
Foundry
Samsung
8 nm
Process Size
8 nm
17.4 billion
Transistors
17.4 billion
392 mm²
Die Size
392 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.6
CUDA
8.6
6.6
Shader Model
6.6
