NVIDIA Rubin Ultra GPU vs NVIDIA Tesla K80

GPU Specs Compare

G

NVIDIA Rubin Ultra GPU

NVIDIA 2027-01
G

NVIDIA Tesla K80

NVIDIA 2014-11

Graphics Card

Release Date
Jan 2027
Nov 2014
Generation
Server Rubin
Tesla
Type
Desktop
Professional
Bus Interface
PCIe 6.0 x16
PCIe 3.0 x16

Clock Speeds

Base Clock
700 MHz
562 MHz
Boost Clock
2267 MHz
824 MHz
Memory Clock
1900 MHz
1253 MHz

Memory

Memory Size
1024GB
12GB
Memory Type
HBM4e
GDDR5
Memory Bus
32768bit
384bit
Bandwidth
31.1TB/s
240.6GB/s

Render Config

SM Count
448
-
Shading Units
57344
2496
TMUs
1792
208
ROPs
24
48
Tensor Cores
1792
-
L1 Cache
256 KB (per SM)
16 KB (per SMX)
L2 Cache
128 MB
1536 KB

Theoretical Performance

Pixel Rate
54.41 GPixel/s
42.85 GPixel/s
Texture Rate
4062.5 GTexel/s
171.4 GTexel/s
FP16 (half)
520.0 TFLOPS
-
FP32 (float)
260.0 TFLOPS
4.113 TFLOPS
FP64 (double)
65.00 TFLOPS
1371 GFLOPS

Graphics Processor

GPU Name
GR110
GK210
Architecture
Rubin Ultra
Kepler 2.0
Foundry
TSMC
TSMC
Process Size
3 nm
28 nm
Transistors
670 billion
7.1 billion
Die Size
2912 mm²
561 mm²
GPU Variant
-
GK210-885-A1

Board Design

TDP
3600W
300W
Suggested PSU
4000 W
700 W
Outputs
No outputs
No outputs
Power Connectors
-
1x 8-pin

Graphics Features

DirectX
N/A
12 (11_1)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
1.1
CUDA
10.7
3.7
Shader Model
N/A
5.1