AMD Radeon Instinct MI325X vs NVIDIA RTX A6000

Comparison of AMD Radeon Instinct MI325X with 288 GB HBM3e and 19,456 cores vs NVIDIA RTX A6000 with 48 GB GDDR6 and 10,752 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

AMD Radeon Instinct MI325X

100.0

AMD Radeon Instinct MI325X

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

NVIDIA RTX A6000

NVIDIA RTX A6000

Contents:

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

Memory

Memory Size

🔥 +500% 288 ГБ
48 GB

Memory Type

HBM3e GDDR6

Memory Bandwidth

🔥 10.3 TB/s
768.0 GB/s

Memory Bus Width

8,192 бит 384 бит

ML Performance

FP16 (Half Precision)

🔥 +1,589% 653.7 TFLOPS
38.71 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +111% 81.72 TFLOPS
38.71 TFLOPS

FP64 (Double Precision)

🔥 +13,412% 81.72 TFLOPS
0.6048 TFLOPS

CUDA Cores

🔥 +81% 19,456
10,752

RT Cores

No 84

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Ampere

SM (Streaming Multiprocessor)

No 84

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No 8.6

Clocks & Performance

Base Clock

🔥 1,000
1,410

Boost Clock

🔥 +17% 2,100
1,800

Memory Clock

🔥 +26% 2,525
2,000

Power Consumption

TDP/TGP

1000 W
🔥 -70% 300 W

Recommended PSU

1400 W
🔥 -50% 700 W

Power Connector

None 8-pin EPS

Rendering

Texture Units (TMU)

🔥 +262% 1,216
336

ROP

No 84

L2 Cache

🔥 +167% 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. 15, 2024 Oct. 5, 2020

Display Outputs

No outputs
4x DisplayPort 1.4a

Renting is cheaper than buying