NVIDIA A100 PCIe 80 GB vs NVIDIA Tesla T10 16 GB

Comparison of NVIDIA A100 PCIe 80 GB with 80 GB HBM2e and 6,912 cores vs NVIDIA Tesla T10 16 GB with 16 GB GDDR6 and 3,584 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA A100 PCIe 80 GB

NVIDIA A100 PCIe 80 GB

MI250 MI250
Instinct MI300X Instinct MI300X
RX 7900 XTX RX 7900 XTX

NVIDIA Tesla T10 16 GB

7.6

NVIDIA Tesla T10 16 GB

7.6

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Additional

Memory

Memory Size

80 GB
🔥 16 ГБ

Memory Type

HBM2e GDDR6

Memory Bandwidth

1.94 TB/s 403.2 GB/s

Memory Bus Width

5,120 бит 256 бит

ML Performance

FP16 (Half Precision)

77.97 TFLOPS
🔥 20.0 TFLOPS

BF16 (Brain Float)

311.84 TFLOPS No

TF32 (TensorFloat)

155.92 No

Compute Power

FP32 (Single Precision)

19.49 TFLOPS
🔥 9.999 TFLOPS

FP64 (Double Precision)

9.746 TFLOPS
🔥 0.3125 TFLOPS

CUDA Cores

6,912
🔥 3,584

RT Cores

No
🔥 56

Architecture & Compatibility

GPU Architecture

Ampere Turing

SM (Streaming Multiprocessor)

108
🔥 56

PCIe Version

PCIe 4.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

🔥 8.0
7.5

Clocks & Performance

Base Clock

1,065
🔥 1,065

Boost Clock

1,410
🔥 1,395

Memory Clock

1,512
🔥 +4% 1,575

Power Consumption

TDP/TGP

300 W
🔥 -50% 150 W

Recommended PSU

700 W
🔥 -36% 450 W

Power Connector

8-pin EPS 1x 8-pin

Rendering

Texture Units (TMU)

432
🔥 224

ROP

No
🔥 56

L2 Cache

80 MB
🔥 6 MB

Additional

Slots

Dual-slot Single-slot

Release Date

June 28, 2021 July 16, 2020

Display Outputs

No outputs
No outputs

Renting is cheaper than buying