NVIDIA GRID K2 vs NVIDIA GRID A100B
We compared two Professional market GPUs: 4GB VRAM GRID K2 and 48GB VRAM GRID A100B to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GRID K2 's Advantages
Lower TDP (225W vs 400W)
NVIDIA GRID A100B 's Advantages
Released 7 years late
Boost Clock1005MHz
More VRAM (48GB vs 4GB)
Larger VRAM bandwidth (1866GB/s vs 160.0GB/s)
5376 additional rendering cores
Score
Benchmark
FP32 (float)
GRID K2
2.289 TFLOPS
GRID A100B
+506%
13.89 TFLOPS
Graphics Card
May 2013
Release Date
May 2020
GRID
Generation
GRID
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
900 MHz
-
Boost Clock
1005 MHz
1250 MHz
Memory Clock
1215 MHz
Memory
4GB
Memory Size
48GB
GDDR5
Memory Type
HBM2e
256bit
Memory Bus
6144bit
160.0GB/s
Bandwidth
1866GB/s
Render Config
-
-
-
-
SM Count
108
1536
Shading Units
6912
128
TMUs
432
32
ROPs
192
-
Tensor Cores
432
-
-
-
16 KB (per SMX)
L1 Cache
192 KB (per SM)
512 KB
L2 Cache
48 MB
-
-
-
Theoretical Performance
23.84 GPixel/s
Pixel Rate
193.0 GPixel/s
95.36 GTexel/s
Texture Rate
434.2 GTexel/s
-
FP16 (half)
55.57 TFLOPS
2.289 TFLOPS
FP32 (float)
13.89 TFLOPS
95.36 GFLOPS
FP64 (double)
6.947 TFLOPS
Board Design
225W
TDP
400W
550 W
Suggested PSU
800 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
None
Graphics Processor
GK104
GPU Name
GA100
GK104-895-A2
GPU Variant
-
Kepler
Architecture
Ampere
TSMC
Foundry
TSMC
28 nm
Process Size
7 nm
3.54 billion
Transistors
54.2 billion
294 mm²
Die Size
826 mm²
Graphics Features
12 (11_0)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.2.175
Vulkan
N/A
3.0
CUDA
8.0
6.5 (5.1)
Shader Model
N/A
