NVIDIA Tesla T4 vs NVIDIA RTX A6000

GPU Specs Compare

G

NVIDIA Tesla T4

NVIDIA 2018-09
G

NVIDIA RTX A6000

NVIDIA 2020-10

Graphics Card

Release Date
Sep 2018
Oct 2020
Generation
Tesla
Quadro Ampere
Type
Professional
Professional
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16

Clock Speeds

Base Clock
585 MHz
1410 MHz
Boost Clock
1590 MHz
1800 MHz
Memory Clock
1250 MHz
2000 MHz

Memory

Memory Size
16GB
48GB
Memory Type
GDDR6
GDDR6
Memory Bus
256bit
384bit
Bandwidth
320.0GB/s
768.0GB/s

Render Config

SM Count
40
84
Shading Units
2560
10752
TMUs
160
336
ROPs
64
112
Tensor Cores
320
336
RT Cores
40
84
L1 Cache
64 KB (per SM)
128 KB (per SM)
L2 Cache
4 MB
6 MB

Theoretical Performance

Pixel Rate
101.8 GPixel/s
201.6 GPixel/s
Texture Rate
254.4 GTexel/s
604.8 GTexel/s
FP16 (half)
65.13 TFLOPS
38.71 TFLOPS
FP32 (float)
8.141 TFLOPS
38.71 TFLOPS
FP64 (double)
254.4 GFLOPS
604.8 GFLOPS

Graphics Processor

GPU Name
TU104
GA102
GPU Variant
TU104-895-A1
-
Architecture
Turing
Ampere
Foundry
TSMC
Samsung
Process Size
12 nm
8 nm
Transistors
13.6 billion
28.3 billion
Die Size
545 mm²
628 mm²

Board Design

TDP
70W
300W
Suggested PSU
250 W
700 W
Outputs
No outputs
4x DisplayPort 1.4a
Power Connectors
None
8-pin EPS

Graphics Features

DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.3
CUDA
7.5
8.6
Shader Model
6.6
6.7

📊 Benchmark

Blender
1,652
5,387
3DMark Time Spy
-
17,742
3DMark Time Spy Extreme
-
9,324
OctaneBench
-
600
3DMark Speed Way
-
4,965