NVIDIA CMP 70HX vs NVIDIA RTX 4000 SFF Ada Generation

Comparison of NVIDIA CMP 70HX with 8 GB GDDR6X and 3,840 cores vs NVIDIA RTX 4000 SFF Ada Generation with 20 GB GDDR6 and 6,144 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA CMP 70HX

NVIDIA CMP 70HX

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

NVIDIA RTX 4000 SFF Ada Generation

9.9

NVIDIA RTX 4000 SFF Ada Generation

9.9

Contents:

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

Memory

Memory Size

8 GB
🔥 +150% 20 ГБ

Memory Type

GDDR6X GDDR6

Memory Bandwidth

608.3 GB/s 280.0 GB/s

Memory Bus Width

256 бит 160 бит

ML Performance

FP16 (Half Precision)

10.71 TFLOPS
🔥 +79% 19.17 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

10.71 TFLOPS
🔥 +79% 19.17 TFLOPS

FP64 (Double Precision)

0.1674 TFLOPS
🔥 +79% 0.2995 TFLOPS

CUDA Cores

3,840
🔥 +60% 6,144

RT Cores

30
🔥 +60% 48

Architecture & Compatibility

GPU Architecture

Ampere Ada Lovelace

SM (Streaming Multiprocessor)

30
🔥 +60% 48

PCIe Version

PCIe 1.0 x4 PCIe 4.0 x16

ML Software Support

CUDA Version

8.6
🔥 8.9

Clocks & Performance

Base Clock

1,365
🔥 720

Boost Clock

1,395
🔥 +12% 1,560

Memory Clock

1,188
🔥 +47% 1,750

Power Consumption

TDP/TGP

unknown 70 W

Recommended PSU

🔥 -20% 200 W
250 W

Power Connector

1x 12-pin None

Rendering

Texture Units (TMU)

120
🔥 +60% 192

ROP

30
🔥 +60% 48

L2 Cache

4 MB
🔥 +1,100% 48 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

March 11, 2021 March 21, 2023

Display Outputs

No outputs
4x mini-DisplayPort 1.4a

Renting is cheaper than buying