NVIDIA GRID K260Q vs Intel Data Center GPU Max Subsystem

GPU Specs Compare

Graphics Card

Release Date
Jun 2013
Jan 2023
Generation
GRID
Data Center GPU
Type
Professional
Professional
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16

Clock Speeds

Memory Clock
1250 MHz
1565 MHz
Base Clock
-
900 MHz
Boost Clock
-
1600 MHz

Memory

Memory Size
2GB
128GB
Memory Type
GDDR5
HBM2e
Memory Bus
256bit
8192bit
Bandwidth
160.0GB/s
3205GB/s

Render Config

Shading Units
1536
16384
TMUs
128
1024
ROPs
32
0
L1 Cache
16 KB (per SMX)
64 KB (per EU)
L2 Cache
512 KB
408 MB
Tensor Cores
-
1024
RT Cores
-
128

Theoretical Performance

Pixel Rate
23.84 GPixel/s
0 MPixel/s
Texture Rate
95.36 GTexel/s
1638 GTexel/s
FP32 (float)
2.289 TFLOPS
52.43 TFLOPS
FP64 (double)
95.36 GFLOPS
52.43 TFLOPS
FP16 (half)
-
52.43 TFLOPS

Graphics Processor

GPU Name
GK104
Ponte Vecchio
Architecture
Kepler
Generation 12.5
Foundry
TSMC
Intel
Process Size
28 nm
10 nm
Transistors
3.54 billion
100 billion
Die Size
294 mm²
1280 mm²

Board Design

TDP
225W
2400W
Suggested PSU
550 W
2800 W
Outputs
No outputs
No outputs
Power Connectors
-
1x 16-pin

Graphics Features

DirectX
12 (11_0)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.1
N/A
CUDA
3.0
-
Shader Model
5.1
6.6