NVIDIA CMP 70HX vs NVIDIA L40-2Q

Comparison of NVIDIA CMP 70HX with 8 GB GDDR6X and 3,840 cores vs NVIDIA L40-2Q with 2 GB GDDR6 and 18,176 cores.

Loading...

Performance Rating

NVIDIA L40-2Q outperforms NVIDIA CMP 70HX by 193.61% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA CMP 70HX

7.7

NVIDIA CMP 70HX

7.7
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA L40-2Q

22.5

NVIDIA L40-2Q

22.5

Contents:

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

Memory

Memory Size

🔥 +300% 8 ГБ
2 ГБ

Memory Type

GDDR6X GDDR6

Memory Bandwidth

608.3 GB/s 864.0 GB/s

Memory Bus Width

256 бит 384 бит

ML Performance

FP16 (Half Precision)

10.71 TFLOPS
🔥 +745% 90.52 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

10.71 TFLOPS
🔥 +745% 90.52 TFLOPS

FP64 (Double Precision)

🔥 0.1674 TFLOPS
No

CUDA Cores

3,840
🔥 +373% 18,176

RT Cores

30
🔥 +373% 142

Architecture & Compatibility

GPU Architecture

Ampere Ada Lovelace

SM (Streaming Multiprocessor)

30
🔥 +373% 142

PCIe Version

PCIe 1.0 x4 PCIe 4.0 x16

ML Software Support

CUDA Version

8.6
🔥 8.9

Clocks & Performance

Base Clock

🔥 +86% 1,365
735

Boost Clock

1,395
🔥 +78% 2,490

Memory Clock

1,188
🔥 +89% 2,250

Power Consumption

TDP/TGP

unknown 300 W

Recommended PSU

🔥 -71% 200 W
700 W

Power Connector

1x 12-pin 1x 16-pin

Rendering

Texture Units (TMU)

120
🔥 +373% 568

ROP

30
🔥 +373% 142

L2 Cache

4 MB
🔥 +2,300% 96 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

July 16, 2021 Oct. 13, 2022

Display Outputs

No outputs
4x DisplayPort 1.4a

Renting is cheaper than buying