NVIDIA CMP 90HX vs NVIDIA RTX PRO 4000 Blackwell SFF

Comparison of NVIDIA CMP 90HX with 10 GB GDDR6X and 6,400 cores vs NVIDIA RTX PRO 4000 Blackwell SFF with 24 GB GDDR7 and 8,960 cores.

Loading...

Performance Rating

NVIDIA RTX PRO 4000 Blackwell SFF outperforms NVIDIA CMP 90HX by 5.57% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA CMP 90HX

12.6

NVIDIA CMP 90HX

12.6
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA RTX PRO 4000 Blackwell SFF

13.3

NVIDIA RTX PRO 4000 Blackwell SFF

13.3

Contents:

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

Memory

Memory Size

10 GB
🔥 +140% 24 ГБ

Memory Type

GDDR6X GDDR7

Memory Bandwidth

760.3 GB/s 432.0 GB/s

Memory Bus Width

320 бит 192 бит

ML Performance

FP16 (Half Precision)

21.89 TFLOPS
🔥 +17% 25.66 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

21.89 TFLOPS
🔥 +17% 25.66 TFLOPS

FP64 (Double Precision)

0.342 TFLOPS
🔥 +17% 0.401 TFLOPS

CUDA Cores

6,400
🔥 +40% 8,960

RT Cores

50
🔥 +40% 70

Architecture & Compatibility

GPU Architecture

Ampere Blackwell 2.0

SM (Streaming Multiprocessor)

50
🔥 +40% 70

PCIe Version

PCIe 1.0 x4 PCIe 5.0 x8

ML Software Support

CUDA Version

8.6
🔥 12.0

Clocks & Performance

Base Clock

🔥 +160% 1,500
577

Boost Clock

🔥 +19% 1,710
1,432

Memory Clock

🔥 +6% 1,188
1,125

Power Consumption

Recommended PSU

700 W
🔥 -64% 250 W

Power Connector

2x 8-pin None

TDP/TGP

320 W
🔥 -78% 70 W

Rendering

Texture Units (TMU)

200
🔥 +40% 280

ROP

50
🔥 +40% 70

L2 Cache

🔥 5 MB
48 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

July 28, 2021 Aug. 11, 2025

Display Outputs

No outputs
4x mini-DisplayPort 2.1b

Renting is cheaper than buying