AMD Radeon Instinct MI355X vs Intel Data Center GPU Max 1350

Comparison of AMD Radeon Instinct MI355X with 288 GB HBM3e and 16,384 cores vs Intel Data Center GPU Max 1350 with 96 GB HBM2e and 14,336 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

AMD Radeon Instinct MI355X

AMD Radeon Instinct MI355X

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

Intel Data Center GPU Max 1350

45.6

Intel Data Center GPU Max 1350

45.6

Contents:

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

Memory

Memory Size

288 GB
🔥 96 ГБ

Memory Type

HBM3e HBM2e

Memory Bandwidth

8.19 TB/s
🔥 2.46 TB/s

Memory Bus Width

8,192 бит 8,192 бит

ML Performance

FP16 (Half Precision)

629.1 TFLOPS
🔥 44.44 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

78.64 TFLOPS
🔥 44.44 TFLOPS

FP64 (Double Precision)

78.64 TFLOPS
🔥 44.44 TFLOPS

CUDA Cores

16,384
🔥 14,336

RT Cores

No
🔥 112

Architecture & Compatibility

GPU Architecture

CDNA 4.0 Generation 12.5

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No No

Clocks & Performance

Base Clock

1,000
🔥 750

Boost Clock

2,400
🔥 1,550

Memory Clock

2,000
🔥 1,200

Power Consumption

TDP/TGP

1400 W
🔥 -68% 450 W

Recommended PSU

1800 W
🔥 -53% 850 W

Power Connector

None No

Rendering

Texture Units (TMU)

1,024
🔥 896

ROP

No
🔥 112

L2 Cache

32 MB
🔥 +1,175% 408 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 OAM Module

Release Date

March 12, 2025 Jan. 10, 2023

Display Outputs

No outputs
No outputs

Renting is cheaper than buying