AMD Radeon Instinct MI325X vs NVIDIA Quadro RTX 8000 Passive

Comparison of AMD Radeon Instinct MI325X with 288 GB HBM3e and 19,456 cores vs NVIDIA Quadro RTX 8000 Passive with 48 GB GDDR6 and 4,608 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

AMD Radeon Instinct MI325X

AMD Radeon Instinct MI325X

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

NVIDIA Quadro RTX 8000 Passive

12.6

NVIDIA Quadro RTX 8000 Passive

12.6

Contents:

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

Memory

Memory Size

288 GB 48 ГБ

Memory Type

HBM3e GDDR6

Memory Bandwidth

10.3 TB/s 624.0 GB/s

Memory Bus Width

8,192 бит 384 бит

ML Performance

FP16 (Half Precision)

653.7 TFLOPS 29.86 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

81.72 TFLOPS 14.93 TFLOPS

FP64 (Double Precision)

81.72 TFLOPS 0.4666 TFLOPS

CUDA Cores

19,456 4,608

RT Cores

No 72

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Turing

SM (Streaming Multiprocessor)

No 72

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

No 7.5

Clocks & Performance

Base Clock

1,000 1,230

Boost Clock

2,100 1,620

Memory Clock

2,525 1,625

Power Consumption

TDP/TGP

1000 W
🔥 -74% 260 W

Recommended PSU

1400 W
🔥 -57% 600 W

Power Connector

None 1x 6-pin + 1x 8-pin

Rendering

Texture Units (TMU)

1,216 288

ROP

No 72

L2 Cache

16 MB 6 MB

Benchmarks

MLPerf, llama2-70b-99.9 (Dummy)

3 596 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

1 946 tokens/s

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

22.4 tokens/s

MLPerf, mixtral-8x7b (fp8)

6 975 tokens/s

Additional

Slots

OAM Module Dual-slot

Release Date

Oct. 12, 2024 Aug. 13, 2018

Display Outputs

No outputs
No outputs

Renting is cheaper than buying