AMD Radeon Instinct MI300X vs AMD Radeon Instinct MI60

Comparison of AMD Radeon Instinct MI300X with 192 GB HBM3 and 19,456 cores vs AMD Radeon Instinct MI60 with 32 GB HBM2 and 4,096 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI300X outperforms AMD Radeon Instinct MI60 by 471.0% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI300X

94.1

AMD Radeon Instinct MI300X

94.1
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

AMD Radeon Instinct MI60

16.5

AMD Radeon Instinct MI60

16.5

Contents:

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

Memory

Memory Size

🔥 +500% 192 ГБ
32 ГБ

Memory Type

HBM3 HBM2

Memory Bandwidth

🔥 +910% 10.3 TB/s
1.02 TB/s

Memory Bus Width

8,192 бит 4,096 бит

ML Performance

FP16 (Half Precision)

🔥 +2,117% 653.7 TFLOPS
29.49 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +454% 81.72 TFLOPS
14.75 TFLOPS

FP64 (Double Precision)

🔥 +1,008% 81.72 TFLOPS
7.373 TFLOPS

CUDA Cores

🔥 +375% 19,456
4,096

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 3.0 GCN 5.1

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No No

Clocks & Performance

Base Clock

🔥 1,000
1,200

Boost Clock

🔥 +17% 2,100
1,800

Memory Clock

🔥 +152% 2,525
1,000

Power Consumption

TDP/TGP

750 W
🔥 -60% 300 W

Recommended PSU

1150 W
🔥 -39% 700 W

Power Connector

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

Rendering

Texture Units (TMU)

🔥 +375% 1,216
256

ROP

No No

L2 Cache

🔥 +300% 16 MB
4 MB

Benchmarks

MLPerf, llama2-70b-99.9 (UNSET)

1 983 tokens/s

MLPerf, llama2-70b-99.9 (fp16)

1 740 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

1 057 tokens/s

MLPerf, llama3.1-405b (UNSET)

30.4 tokens/s

MLPerf, llama3.1-405b (fp16)

34.8 tokens/s

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

232.9 tokens/s

MLPerf, mixtral-8x7b (fp8)

5 975 tokens/s

Additional

Slots

OAM Module Dual-slot

Release Date

Dec. 6, 2023 Nov. 18, 2018

Display Outputs

No outputs
1x mini-DisplayPort 1.4a

Renting is cheaper than buying