NVIDIA P104-100 vs NVIDIA RTX PRO 4000 Blackwell SFF

Comparison of NVIDIA P104-100 with 4 GB GDDR5X and 1,920 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 P104-100 by 183.55% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA P104-100

4.7

NVIDIA P104-100

4.7
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

4 GB
🔥 +500% 24 ГБ

Memory Type

GDDR5X GDDR7

Memory Bandwidth

320.3 GB/s 432.0 GB/s

Memory Bus Width

256 бит 192 бит

ML Performance

FP16 (Half Precision)

0.104 TFLOPS
🔥 +24,573% 25.66 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

6.655 TFLOPS
🔥 +286% 25.66 TFLOPS

FP64 (Double Precision)

0.208 TFLOPS
🔥 +93% 0.401 TFLOPS

CUDA Cores

1,920
🔥 +367% 8,960

RT Cores

No
🔥 70

Architecture & Compatibility

GPU Architecture

Pascal Blackwell 2.0

SM (Streaming Multiprocessor)

15
🔥 +367% 70

PCIe Version

PCIe 1.0 x4 PCIe 5.0 x8

ML Software Support

CUDA Version

6.1
🔥 12.0

Clocks & Performance

Base Clock

1,607
🔥 577

Boost Clock

1,733
🔥 1,432

Memory Clock

1,251
🔥 1,125

Power Consumption

Recommended PSU

🔥 -20% 200 W
250 W

Power Connector

1x 8-pin None

TDP/TGP

unknown 70 W

Rendering

Texture Units (TMU)

120
🔥 +133% 280

ROP

No
🔥 70

L2 Cache

2 MB
🔥 +2,300% 48 MB

Additional

Slots

Dual-slot Dual-slot

Release Date

Dec. 12, 2017 Aug. 11, 2025

Display Outputs

No outputs
4x mini-DisplayPort 2.1b

Renting is cheaper than buying