AMD Radeon Instinct MI355X vs NVIDIA PG506-207

Comparison of AMD Radeon Instinct MI355X with 288 GB HBM3e and 16,384 cores vs NVIDIA PG506-207 with 24 GB HBM2 and 3,584 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

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 PG506-207

NVIDIA PG506-207

Contents:

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

Memory

Memory Size

🔥 +1,100% 288 ГБ
24 GB

Memory Type

HBM3e HBM2

Memory Bandwidth

🔥 8.19 TB/s
933.1 GB/s

Memory Bus Width

8,192 бит 3,072 бит

ML Performance

FP16 (Half Precision)

🔥 +5,996% 629.1 TFLOPS
10.32 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +662% 78.64 TFLOPS
10.32 TFLOPS

FP64 (Double Precision)

🔥 +1,424% 78.64 TFLOPS
5.161 TFLOPS

CUDA Cores

🔥 +357% 16,384
3,584

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 4.0 Ampere

SM (Streaming Multiprocessor)

No 56

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No 8.0

Clocks & Performance

Base Clock

🔥 +8% 1,000
930

Boost Clock

🔥 +67% 2,400
1,440

Memory Clock

🔥 +65% 2,000
1,215

Power Consumption

TDP/TGP

1400 W
🔥 -88% 165 W

Recommended PSU

1800 W
🔥 -75% 450 W

Power Connector

None 8-pin EPS

Rendering

Texture Units (TMU)

🔥 +357% 1,024
224

ROP

No No

L2 Cache

🔥 16 MB
24 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 April 12, 2021

Display Outputs

No outputs
No outputs

Renting is cheaper than buying