AMD Radeon Instinct MI355X vs AMD Radeon RX Vega 64

Comparison of AMD Radeon Instinct MI355X with 288 GB HBM3e and 16,384 cores vs AMD Radeon RX Vega 64 with 8 GB HBM2 and 4,096 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI355X outperforms AMD Radeon RX Vega 64 by 845.6% 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

AMD Radeon RX Vega 64

9.9

AMD Radeon RX Vega 64

9.9

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 HBM2

Memory Bandwidth

🔥 8.19 TB/s
483.8 GB/s

Memory Bus Width

8,192 бит 2,048 бит

ML Performance

FP16 (Half Precision)

🔥 +2,384% 629.1 TFLOPS
25.33 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +521% 78.64 TFLOPS
12.66 TFLOPS

FP64 (Double Precision)

🔥 +9,834% 78.64 TFLOPS
0.7916 TFLOPS

CUDA Cores

🔥 +300% 16,384
4,096

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 4.0 GCN 5.0

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

No No

Clocks & Performance

Base Clock

🔥 1,000
1,247

Boost Clock

🔥 +55% 2,400
1,546

Memory Clock

🔥 +112% 2,000
945

Power Consumption

TDP/TGP

1400 W
🔥 -79% 295 W

Recommended PSU

1800 W
🔥 -67% 600 W

Power Connector

None 2x 8-pin

Rendering

Texture Units (TMU)

🔥 +300% 1,024
256

ROP

No No

L2 Cache

🔥 +300% 16 MB
4 MB

Benchmarks

MLPerf, llama2-70b-99.9 (mxfp4)

10 129 tokens/s

MLPerf, llama3.1-405b (mxfp4)

252.4 tokens/s

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

47.1 tokens/s

Additional

Slots

OAM Module Dual-slot

Release Date

July 15, 2025 Aug. 7, 2017

Display Outputs

No outputs
1x HDMI 2.0b
3x DisplayPort 1.4a

Renting is cheaper than buying