AMD Radeon Instinct MI300X vs AMD Radeon Pro W6800X Duo

Comparison of AMD Radeon Instinct MI300X with 192 GB HBM3 and 19,456 cores vs AMD Radeon Pro W6800X Duo with 32 GB GDDR6 and 3,840 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

AMD Radeon Instinct MI300X

AMD Radeon Instinct MI300X

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

AMD Radeon Pro W6800X Duo

AMD Radeon Pro W6800X Duo

Contents:

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

Memory

Memory Size

192 GB 32 GB

Memory Type

HBM3 GDDR6

Memory Bandwidth

10.3 TB/s 512.0 GB/s

Memory Bus Width

8,192 бит 256 бит

ML Performance

FP16 (Half Precision)

653.7 TFLOPS 30.21 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

81.72 TFLOPS 15.11 TFLOPS

FP64 (Double Precision)

81.72 TFLOPS 0.9442 TFLOPS

CUDA Cores

19,456 3,840

RT Cores

No 60

Architecture & Compatibility

GPU Architecture

CDNA 3.0 RDNA 2.0

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 Apple MPX

ML Software Support

CUDA Version

No No

Clocks & Performance

Base Clock

1,000 1,800

Boost Clock

2,100 1,967

Memory Clock

2,525 2,000

Power Consumption

TDP/TGP

750 W
🔥 -47% 400 W

Recommended PSU

1150 W
🔥 -30% 800 W

Power Connector

None No

Rendering

Texture Units (TMU)

1,216 240

ROP

No 60

L2 Cache

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 Quad-slot

Release Date

Dec. 6, 2023 Aug. 3, 2021

Display Outputs

No outputs
1x HDMI 2.1
4x Thunderbolt

Renting is cheaper than buying