AMD Radeon Instinct MI325X vs Microsoft RTX 4050 Mobile

Comparison of AMD Radeon Instinct MI325X with 288 GB HBM3e and 19,456 cores vs Microsoft RTX 4050 Mobile with 6 GB GDDR6 and 2,560 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

AMD Radeon Instinct MI325X

AMD Radeon Instinct MI325X

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

Microsoft RTX 4050 Mobile

5.3

Microsoft RTX 4050 Mobile

5.3

Contents:

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

Memory

Memory Size

288 GB
🔥 6 ГБ

Memory Type

HBM3e GDDR6

Memory Bandwidth

10.3 TB/s 192.0 GB/s

Memory Bus Width

8,192 бит 96 бит

ML Performance

FP16 (Half Precision)

653.7 TFLOPS
🔥 10.91 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

81.72 TFLOPS
🔥 10.91 TFLOPS

FP64 (Double Precision)

81.72 TFLOPS
🔥 +208,417% 170,400.0 TFLOPS

CUDA Cores

19,456
🔥 2,560

RT Cores

No
🔥 20

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Ada Lovelace

SM (Streaming Multiprocessor)

No
🔥 20

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x8

ML Software Support

CUDA Version

No 8.9

Clocks & Performance

Base Clock

1,000
🔥 +78% 1,785

Boost Clock

2,100
🔥 +1% 2,130

Memory Clock

2,525
🔥 2,000

Power Consumption

TDP/TGP

1000 W
🔥 -95% 50 W

Recommended PSU

1400 W No

Power Connector

None None

Rendering

Texture Units (TMU)

1,216
🔥 80

ROP

No
🔥 20

L2 Cache

16 MB
🔥 12 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 IGP

Release Date

Oct. 12, 2024 Jan. 3, 2023

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying