NVIDIA CMP 170HX 8 GB vs NVIDIA CMP 70HX

Comparison of NVIDIA CMP 170HX 8 GB with 8 GB HBM2e and 4,480 cores vs NVIDIA CMP 70HX with 8 GB GDDR6X and 3,840 cores.

Loading...

Performance Rating

NVIDIA CMP 170HX 8 GB outperforms NVIDIA CMP 70HX by 72.88% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA CMP 170HX 8 GB

13.3

NVIDIA CMP 170HX 8 GB

13.3
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA CMP 70HX

7.7

NVIDIA CMP 70HX

7.7

Contents:

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

Memory

Memory Size

8 ГБ 8 ГБ

Memory Type

HBM2e GDDR6X

Memory Bandwidth

🔥 1.49 TB/s
608.3 GB/s

Memory Bus Width

4,096 бит 256 бит

ML Performance

FP16 (Half Precision)

🔥 +372% 50.53 TFLOPS
10.71 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +18% 12.63 TFLOPS
10.71 TFLOPS

FP64 (Double Precision)

🔥 +3,674% 6.317 TFLOPS
0.1674 TFLOPS

CUDA Cores

🔥 +17% 4,480
3,840

RT Cores

No
🔥 30

Architecture & Compatibility

GPU Architecture

Ampere Ampere

SM (Streaming Multiprocessor)

🔥 +133% 70
30

PCIe Version

PCIe 1.0 x4 PCIe 1.0 x4

ML Software Support

CUDA Version

8.0
🔥 8.6

Clocks & Performance

Base Clock

1,140
🔥 +20% 1,365

Boost Clock

🔥 +1% 1,410
1,395

Memory Clock

🔥 +23% 1,458
1,188

Power Consumption

TDP/TGP

250 W unknown

Recommended PSU

600 W
🔥 -67% 200 W

Power Connector

2x 8-pin 1x 12-pin

Rendering

Texture Units (TMU)

🔥 +133% 280
120

ROP

No
🔥 30

L2 Cache

🔥 +100% 8 MB
4 MB

Additional

Slots

IGP Dual-slot

Release Date

Sept. 1, 2021 July 16, 2021

Display Outputs

No outputs
No outputs

Renting is cheaper than buying