GeForce RTX 4080 vs GeForce RTX 3070 Ti 16 GB
We compared two Desktop platform GPUs: 16GB VRAM GeForce RTX 4080 and 16GB VRAM GeForce RTX 3070 Ti 16 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 4080 's Advantages
Boost Clock has increased by 42% (2505MHz vs 1770MHz)
Larger VRAM bandwidth (716.8GB/s vs 608.3GB/s)
3584 additional rendering cores
GeForce RTX 3070 Ti 16 GB 's Advantages
Lower TDP (290W vs 320W)
Score
Benchmark
FP32 (float)
GeForce RTX 4080
+124%
48740
GeForce RTX 3070 Ti 16 GB
21750
3DMark Time Spy
GeForce RTX 4080
+89%
28173
GeForce RTX 3070 Ti 16 GB
14872
3DMark Time Spy Extreme
GeForce RTX 4080
+88%
14002
GeForce RTX 3070 Ti 16 GB
7416
3DMark Speed Way
GeForce RTX 4080
+92%
7254
GeForce RTX 3070 Ti 16 GB
3761
Graphics Card
Sep 2022
Release Date
Unknown
GeForce 40
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
2205 MHz
Base Clock
1575 MHz
2505 MHz
Boost Clock
1770 MHz
1400 MHz
Memory Clock
1188 MHz
Memory
16GB
Memory Size
16GB
GDDR6X
Memory Type
GDDR6X
256bit
Memory Bus
256bit
716.8GB/s
Bandwidth
608.3GB/s
Render Config
76
SM Count
48
9728
Shading Units
6144
304
TMUs
192
112
ROPs
96
304
Tensor Cores
192
76
RT Cores
48
128 KB (per SM)
L1 Cache
128 KB (per SM)
64 MB
L2 Cache
4 MB
Theoretical Performance
280.6 GPixel/s
Pixel Rate
169.9 GPixel/s
761.5 GTexel/s
Texture Rate
339.8 GTexel/s
48.74 TFLOPS
FP16 (half)
21.75 TFLOPS
48.74 TFLOPS
FP32 (float)
21.75 TFLOPS
761.5 GFLOPS
FP64 (double)
339.8 GFLOPS
Board Design
320W
TDP
290W
700 W
Suggested PSU
600 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 12-pin
Graphics Processor
AD103
GPU Name
GA104
AD103-300-A1
GPU Variant
GA104-401-A1
Ada Lovelace
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
45.9 billion
Transistors
17.4 billion
379 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
8.9
CUDA
8.6
6.7
Shader Model
6.6
