NVIDIA RTX PRO 4000 Blackwell SFF vs NVIDIA Tesla P10

Comparison of NVIDIA RTX PRO 4000 Blackwell SFF with 24 GB GDDR7 and 8,960 cores vs NVIDIA Tesla P10 with 24 GB GDDR5X and 3,840 cores.

Loading...

Performance Rating

NVIDIA RTX PRO 4000 Blackwell SFF outperforms NVIDIA Tesla P10 by 32.17% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA RTX PRO 4000 Blackwell SFF

13.3

NVIDIA RTX PRO 4000 Blackwell SFF

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

NVIDIA Tesla P10

10.0

NVIDIA Tesla P10

10.0

Contents:

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

Memory

Memory Size

🔥 24 ГБ
24 GB

Memory Type

GDDR7 GDDR5X

Memory Bandwidth

432.0 GB/s 694.3 GB/s

Memory Bus Width

192 бит 384 бит

ML Performance

FP16 (Half Precision)

🔥 +14,219% 25.66 TFLOPS
0.1792 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +124% 25.66 TFLOPS
11.47 TFLOPS

FP64 (Double Precision)

🔥 +12% 0.401 TFLOPS
0.3583 TFLOPS

CUDA Cores

🔥 +133% 8,960
3,840

RT Cores

🔥 70
No

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Pascal

SM (Streaming Multiprocessor)

🔥 +133% 70
30

PCIe Version

PCIe 5.0 x8 PCIe 3.0 x16

ML Software Support

CUDA Version

🔥 12.0
6.1

Clocks & Performance

Base Clock

🔥 577
1,025

Boost Clock

🔥 1,432
1,493

Memory Clock

🔥 1,125
1,808

Power Consumption

Recommended PSU

🔥 -44% 250 W
450 W

Power Connector

None 1x 8-pin

TDP/TGP

🔥 -53% 70 W
150 W

Rendering

Texture Units (TMU)

🔥 +17% 280
240

ROP

🔥 70
No

L2 Cache

🔥 +1,500% 48 MB
3 MB

Additional

Slots

Dual-slot Single-slot

Release Date

Aug. 11, 2025 Sept. 13, 2016

Display Outputs

4x mini-DisplayPort 2.1b
No outputs

Renting is cheaper than buying