GeForce RTX 3070 vs NVIDIA P104 100 8 GB
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3070 and 48GB
GB VRAM NVIDIA P104 100 8 GB to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3070 's Advantages
Released 2 years and 9 months late
More VRAM (8GB vs 48GB)
Larger VRAM bandwidth (448.0GB/s vs 320.3GB/s)
3968 additional rendering cores
NVIDIA P104 100 8 GB 's Advantages
Boost Clock has increased by 0% (1733MHz vs 1725MHz)
Score
Benchmark
FP32 (float)
GeForce RTX 3070
+205%
20310
NVIDIA P104 100 8 GB
6655
Graphics Card
Sep 2020
Release Date
Dec 2017
GeForce 30
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 1.0 x4
Clock Speeds
1500 MHz
Base Clock
1607 MHz
1725 MHz
Boost Clock
1733 MHz
1750 MHz
Memory Clock
1251 MHz
Memory
8GB
Memory Size
48GB
GB
GDDR6
Memory Type
GDDR5X
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
320.3GB/s
Render Config
46
SM Count
15
5888
Shading Units
1920
184
TMUs
120
96
ROPs
64
184
Tensor Cores
-
46
RT Cores
-
128 KB (per SM)
L1 Cache
48 KB (per SM)
4 MB
L2 Cache
2 MB
Theoretical Performance
165.6 GPixel/s
Pixel Rate
110.9 GPixel/s
317.4 GTexel/s
Texture Rate
208.0 GTexel/s
20.31 TFLOPS
FP16 (half)
104.0 GFLOPS
20.31 TFLOPS
FP32 (float)
6.655 TFLOPS
317.4 GFLOPS
FP64 (double)
208.0 GFLOPS
Board Design
220W
TDP
Unknown
550 W
Suggested PSU
200 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
No outputs
1x 12-pin
Power Connectors
1x 8-pin
Graphics Processor
GA104
GPU Name
GP104
GA104-300-A1
GPU Variant
GP104-100-A1
Ampere
Architecture
Pascal
Samsung
Foundry
TSMC
8 nm
Process Size
16 nm
17.4 billion
Transistors
7.2 billion
392 mm²
Die Size
314 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.6
CUDA
6.1
6.6
Shader Model
6.8
