AMD Radeon Instinct MI355X vs NVIDIA Tesla PG503-216

Comparison of AMD Radeon Instinct MI355X with 288 GB HBM3e and 16,384 cores vs NVIDIA Tesla PG503-216 with 32 GB HBM2 and 5,120 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI355X outperforms NVIDIA Tesla PG503-216 by 437.78% 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 PG503-216

17.4

NVIDIA Tesla PG503-216

17.4

Contents:

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

Memory

Memory Size

🔥 +800% 288 ГБ
32 ГБ

Memory Type

HBM3e HBM2

Memory Bandwidth

🔥 +625% 8.19 TB/s
1.13 TB/s

Memory Bus Width

8,192 бит 4,096 бит

ML Performance

FP16 (Half Precision)

🔥 +1,908% 629.1 TFLOPS
31.33 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +402% 78.64 TFLOPS
15.67 TFLOPS

FP64 (Double Precision)

🔥 +904% 78.64 TFLOPS
7.834 TFLOPS

CUDA Cores

🔥 +220% 16,384
5,120

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 4.0 Volta

SM (Streaming Multiprocessor)

No 80

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

No 7.0

Clocks & Performance

Base Clock

🔥 1,000
1,312

Boost Clock

🔥 +57% 2,400
1,530

Memory Clock

🔥 +81% 2,000
1,106

Power Consumption

TDP/TGP

1400 W
🔥 -82% 250 W

Recommended PSU

1800 W
🔥 -67% 600 W

Power Connector

None None

Rendering

Texture Units (TMU)

🔥 +220% 1,024
320

ROP

No No

L2 Cache

🔥 +167% 16 MB
6 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 Dual-slot

Release Date

July 15, 2025 Nov. 26, 2019

Display Outputs

No outputs
No outputs

Renting is cheaper than buying