AMD Radeon Instinct MI250 vs Intel Data Center GPU Max Subsystem

Comparison of AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs Intel Data Center GPU Max Subsystem with 128 GB HBM2e and 16,384 cores.

Loading...

Performance Rating

Intel Data Center GPU Max Subsystem outperforms AMD Radeon Instinct MI250 by 7.96% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI250

50.9

AMD Radeon Instinct MI250

50.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

Intel Data Center GPU Max Subsystem

54.9

Intel Data Center GPU Max Subsystem

54.9

Contents:

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

Memory

Memory Size

128 ГБ 128 ГБ

Memory Type

HBM2e HBM2e

Memory Bandwidth

3.28 TB/s
🔥 3.21 TB/s

Memory Bus Width

8,192 бит 8,192 бит

ML Performance

FP16 (Half Precision)

🔥 +591% 362.1 TFLOPS
52.43 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

45.26 TFLOPS
🔥 +16% 52.43 TFLOPS

FP64 (Double Precision)

45.26 TFLOPS
🔥 +16% 52.43 TFLOPS

CUDA Cores

13,312
🔥 +23% 16,384

RT Cores

No
🔥 128

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Generation 12.5

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No No

Clocks & Performance

Base Clock

🔥 +11% 1,000
900

Boost Clock

🔥 +6% 1,700
1,600

Memory Clock

🔥 +2% 1,600
1,565

Power Consumption

TDP/TGP

🔥 -79% 500 W
2400 W

Recommended PSU

🔥 -68% 900 W
2800 W

Power Connector

2x 8-pin 1x 16-pin

Rendering

Texture Units (TMU)

832
🔥 +23% 1,024

ROP

No
🔥 128

L2 Cache

16 MB
🔥 +2,450% 408 MB

Benchmarks

llama.cpp, llama-2-7b-Q4_0

63.9 tokens/s

Additional

Slots

Dual-slot Dual-slot

Release Date

Nov. 8, 2021 Jan. 10, 2023

Display Outputs

No outputs
No outputs

Renting is cheaper than buying