AMD Radeon Instinct MI355X vs NVIDIA Tesla P4

Comparison of AMD Radeon Instinct MI355X with 288 GB HBM3e and 16,384 cores vs NVIDIA Tesla P4 with 8 GB GDDR5 and 2,560 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI355X outperforms NVIDIA Tesla P4 by 2,069.84% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI355X

93.5

AMD Radeon Instinct MI355X

93.5
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA Tesla P4

4.3

NVIDIA Tesla P4

4.3

Contents:

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

Memory

Memory Size

🔥 +3,500% 288 ГБ
8 ГБ

Memory Type

HBM3e GDDR5

Memory Bandwidth

🔥 8.19 TB/s
192.3 GB/s

Memory Bus Width

8,192 бит 256 бит

ML Performance

FP16 (Half Precision)

🔥 +606% 629.1 TFLOPS
89.12 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +1,279% 78.64 TFLOPS
5.704 TFLOPS

FP64 (Double Precision)

🔥 +44,030% 78.64 TFLOPS
0.1782 TFLOPS

CUDA Cores

🔥 +540% 16,384
2,560

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 4.0 Pascal

SM (Streaming Multiprocessor)

No 20

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

No 6.1

Clocks & Performance

Base Clock

🔥 +13% 1,000
886

Boost Clock

🔥 +115% 2,400
1,114

Memory Clock

🔥 +33% 2,000
1,502

Power Consumption

TDP/TGP

1400 W
🔥 -95% 75 W

Recommended PSU

1800 W
🔥 -86% 250 W

Power Connector

None None

Rendering

Texture Units (TMU)

🔥 +540% 1,024
160

ROP

No No

L2 Cache

🔥 +700% 16 MB
2 MB

Benchmarks

MLPerf, llama2-70b-99.9 (mxfp4)

10 129 tokens/s

MLPerf, llama3.1-405b (mxfp4)

252.4 tokens/s

Additional

Slots

OAM Module Single-slot

Release Date

July 15, 2025 Sept. 13, 2016

Display Outputs

No outputs
No outputs

Renting is cheaper than buying