AMD Radeon Instinct MI300X vs AMD Radeon Pro 460

Comparison AMD Radeon Instinct MI300X with 192 GB HBM3 and 19,456 cores vs AMD Radeon Pro 460 with 4 GB GDDR5 and 1,024 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI300X outperforms AMD Radeon Pro 460 by 5,603.03% 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 Pro 460

1.7

AMD Radeon Pro 460

1.7

Expert Comparison

AMD Radeon Instinct MI300X значительно превосходит Radeon Pro 460 по многим параметрам: имеет больше ядер (19456 против 1024), большую память (192 ГБ HBM3 против 4 ГБ GDDR5), большую пропускную способность (10.3 TB/s против 81.28 GB/s) и более высокий индекс производительности (94.1 против 1.6). MI300X подходит для вычислений, машинного обучения и других вычислительно интенсивных задач, в то время как Radeon Pro 460 более подходящ для офисных приложений и базовых задач визуализации.

Contents:

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

Memory

Memory Size

🔥 +4,700% 192 ГБ
4 GB

Memory Type

HBM3 GDDR5

Memory Bandwidth

🔥 10.3 TB/s
81.28 GB/s

Memory Bus Width

8,192 бит 128 бит

ML Performance

FP16 (Half Precision)

🔥 +35,083% 653.7 TFLOPS
1.858 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +4,298% 81.72 TFLOPS
1.858 TFLOPS

FP64 (Double Precision)

🔥 +70,288% 81.72 TFLOPS
0.1161 TFLOPS

CUDA Cores

🔥 +1,800% 19,456
1,024

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 3.0 GCN 4.0

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x8

ML Software Support

CUDA Version

No No

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

🔥 +18% 1,000
850

Boost Clock

🔥 +132% 2,100
907

Memory Clock

🔥 +99% 2,525
1,270

Power Consumption

Recommended PSU

1150 W No

Power Connector

None None

TDP/TGP

750 W
🔥 -95% 35 W

Rendering

Texture Units (TMU)

🔥 +1,800% 1,216
64

ROP

No No

L2 Cache

🔥 16 MB
1024 KB

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 IGP

Release Date

Dec. 6, 2023 Oct. 30, 2016

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying