AMD Radeon Instinct MI325X vs NVIDIA H200 NVL

Comparison of AMD Radeon Instinct MI325X with 288 GB HBM3e and 19,456 cores vs NVIDIA H200 NVL with 141 GB HBM3e and 16,896 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI325X outperforms NVIDIA H200 NVL by 57.13% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI325X

100.0

AMD Radeon Instinct MI325X

100.0
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA H200 NVL

63.6

NVIDIA H200 NVL

63.6

Contents:

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

Memory

Memory Size

🔥 +104% 288 ГБ
141 ГБ

Memory Type

HBM3e HBM3e

Memory Bandwidth

🔥 +111% 10.3 TB/s
4.89 TB/s

Memory Bus Width

8,192 бит 6,144 бит

ML Performance

FP16 (Half Precision)

🔥 +171% 653.7 TFLOPS
241.3 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +35% 81.72 TFLOPS
60.32 TFLOPS

FP64 (Double Precision)

🔥 +171% 81.72 TFLOPS
30.16 TFLOPS

CUDA Cores

🔥 +15% 19,456
16,896

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Hopper

SM (Streaming Multiprocessor)

No
🔥 132

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No 9.0

Clocks & Performance

Base Clock

1,000
🔥 +36% 1,365

Boost Clock

🔥 +18% 2,100
1,785

Memory Clock

🔥 +59% 2,525
1,593

Power Consumption

TDP/TGP

1000 W
🔥 -40% 600 W

Recommended PSU

1400 W
🔥 -29% 1000 W

Power Connector

None 8-pin EPS

Rendering

Texture Units (TMU)

🔥 +130% 1,216
528

ROP

No No

L2 Cache

16 MB
🔥 +212% 50 MB

Benchmarks

MLPerf, llama2-70b-99.9 (Dummy)

3 596 tokens/s

MLPerf, llama2-70b-99.9 (fp4)

7 436 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

1 946 tokens/s

MLPerf, llama3.1-405b (fp4)

130.5 tokens/s

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

22.4 tokens/s

MLPerf, deepseek-r1 (fp4)

2 327 tokens/s

MLPerf, mixtral-8x7b (fp8)

6 975 tokens/s

Additional

Slots

OAM Module Dual-slot

Release Date

Oct. 15, 2024 Nov. 18, 2024

Display Outputs

No outputs
No outputs

Renting is cheaper than buying