NVIDIA A16 PCIe vs Intel Data Center GPU Max 1350
GPU · Specs Compare
Graphics Card
Release Date
Apr 2021
Jan 2023
Generation
Tesla
Data Center GPU
Type
Desktop
Professional
Bus Interface
PCIe 4.0 x8
PCIe 5.0 x16
Clock Speeds
Base Clock
885 MHz
750 MHz
Boost Clock
1695 MHz
1550 MHz
Memory Clock
1812 MHz
1200 MHz
Memory
Memory Size
16GB
96GB
Memory Type
GDDR6
HBM2e
Memory Bus
128bit
8192bit
Bandwidth
231.9GB/s
2458GB/s
Render Config
SM Count
10
—
Shading Units
1280
14336
TMUs
40
896
ROPs
32
0
Tensor Cores
40
896
RT Cores
10
112
L1 Cache
128 KB (per SM)
64 KB (per EU)
L2 Cache
2 MB
408 MB
Theoretical Performance
Pixel Rate
54.24 GPixel/s
0 MPixel/s
Texture Rate
67.80 GTexel/s
1389 GTexel/s
FP16 (half)
4.339 TFLOPS
44.44 TFLOPS
FP32 (float)
4.339 TFLOPS
44.44 TFLOPS
FP64 (double)
135.6 GFLOPS
44.44 TFLOPS
Graphics Processor
GPU Name
GA107
Ponte Vecchio
Architecture
Ampere
Generation 12.5
Foundry
Samsung
Intel
Process Size
8 nm
10 nm
Transistors
Unknown
100 billion
Die Size
Unknown
1280 mm²
Board Design
TDP
250W
450W
Suggested PSU
600 W
850 W
Outputs
No outputs
No outputs
Power Connectors
8-pin EPS
—
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
8.6
—
Shader Model
6.6
6.6
Benchmark
Blender
510
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.