NVIDIA GeForce RTX 3080 Ti Mobile vs NVIDIA GeForce RTX 4070
We compared a Mobile platform GPU: 16GB VRAM GeForce RTX 3080 Ti Mobile and a Desktop platform GPU: 12GB VRAM GeForce RTX 4070 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 3080 Ti Mobile 's Advantages
More VRAM (16GB vs 12GB)
Larger VRAM bandwidth (512.0GB/s vs 504.2GB/s)
1536 additional rendering cores
Lower TDP (115W vs 200W)
NVIDIA GeForce RTX 4070 's Advantages
Released 1 years and 3 months late
Boost Clock has increased by 96% (2475MHz vs 1260MHz)
Score
Benchmark
FP32 (float)
GeForce RTX 3080 Ti Mobile
18.71 TFLOPS
GeForce RTX 4070
+55%
29.15 TFLOPS
3DMark Time Spy
GeForce RTX 3080 Ti Mobile
12905
GeForce RTX 4070
+38%
17887
3DMark Time Spy Extreme
GeForce RTX 3080 Ti Mobile
6164
GeForce RTX 4070
+28%
7907
3DMark Speed Way
GeForce RTX 3080 Ti Mobile
3147
GeForce RTX 4070
+75%
5508
Blender
GeForce RTX 3080 Ti Mobile
3726
GeForce RTX 4070
+56%
5818
OctaneBench
GeForce RTX 3080 Ti Mobile
352
GeForce RTX 4070
+81%
640
Graphics Card
Jan 2022
Release Date
Apr 2023
GeForce 30 Mobile
Generation
GeForce 40
Mobile
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
810 MHz
Base Clock
1920 MHz
1260 MHz
Boost Clock
2475 MHz
2000 MHz
Memory Clock
1313 MHz
Memory
16GB
Memory Size
12GB
GDDR6
Memory Type
GDDR6X
256bit
Memory Bus
192bit
512.0GB/s
Bandwidth
504.2GB/s
Render Config
-
-
-
58
SM Count
46
7424
Shading Units
5888
232
TMUs
184
96
ROPs
64
232
Tensor Cores
184
58
RT Cores
46
128 KB (per SM)
L1 Cache
128 KB (per SM)
4 MB
L2 Cache
36 MB
-
-
-
Theoretical Performance
121.0 GPixel/s
Pixel Rate
158.4 GPixel/s
292.3 GTexel/s
Texture Rate
455.4 GTexel/s
18.71 TFLOPS
FP16 (half)
29.15 TFLOPS
18.71 TFLOPS
FP32 (float)
29.15 TFLOPS
292.3 GFLOPS
FP64 (double)
455.4 GFLOPS
Board Design
115W
TDP
200W
-
Suggested PSU
550 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
None
Power Connectors
1x 16-pin
Graphics Processor
GA103S
GPU Name
AD104
GN20-E8-A1
GPU Variant
AD104-250-A1
Ampere
Architecture
Ada Lovelace
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
Unknown
Transistors
35.8 billion
496 mm²
Die Size
295 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
8.9
6.5
Shader Model
6.7
