GeForce RTX 4090 vs GeForce RTX 3070 6144 SP
We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 4090 and 8GB VRAM GeForce RTX 3070 6144 SP to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 4090 Advantages
Boost Clock has increased by 42% (2520MHz vs 1770MHz)
More VRAM (24GB vs 8GB)
Larger VRAM bandwidth (1.01TB/s vs 448.0GB/s)
10240 additional rendering cores
GeForce RTX 3070 6144 SP Advantages
Lower TDP (290W vs 450W)
Score
Benchmark
FP32 (float)
GeForce RTX 4090
+279%
82580
GeForce RTX 3070 6144 SP
21750
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
2235 MHz
Base Clock
1740 MHz
2520 MHz
Boost Clock
1770 MHz
1313 MHz
Memory Clock
1750 MHz
Memory
24GB
Memory Size
8GB
GDDR6X
Memory Type
GDDR6
384bit
Memory Bus
256bit
1.01TB/s
Bandwidth
448.0GB/s
Render Config
128
SM Count
48
16384
Shading Units
6144
512
TMUs
192
176
ROPs
96
512
Tensor Cores
192
128
RT Cores
48
128 KB (per SM)
L1 Cache
128 KB (per SM)
72 MB
L2 Cache
4 MB
Theoretical Performance
443.5 GPixel/s
Pixel Rate
169.9 GPixel/s
1290 GTexel/s
Texture Rate
339.8 GTexel/s
82.58 TFLOPS
FP16 (half)
21.75 TFLOPS
82.58 TFLOPS
FP32 (float)
21.75 TFLOPS
1290 GFLOPS
FP64 (double)
339.8 GFLOPS
Board Design
450W
TDP
290W
850 W
Suggested PSU
600 W
1x HDMI 2.1
3x DisplayPort 1.4a
3x DisplayPort 1.4a
Outputs
1x HDMI 2.13x DisplayPort 1.4a
1x 16-pin
Power Connectors
1x 8-pin
Graphics Processor
AD102
GPU Name
GA104
AD102-300-A1
GPU Variant
-
Ada Lovelace
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
76.3 billion
Transistors
17.4 billion
609 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
6.8
Shader Model
6.8
