AFOX RTX 3080 Ti V3 vs AMD Radeon Instinct MI325X

Comparison of AFOX RTX 3080 Ti V3 with 12 GB GDDR6X and 10,240 cores vs AMD Radeon Instinct MI325X with 288 GB HBM3e and 19,456 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

AFOX RTX 3080 Ti V3

AFOX RTX 3080 Ti V3

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

AMD Radeon Instinct MI325X

AMD Radeon Instinct MI325X

Contents:

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

Memory

Memory Size

12 GB 288 GB

Memory Type

GDDR6X HBM3e

Memory Bandwidth

912.4 GB/s 10.3 TB/s

Memory Bus Width

384 бит 8,192 бит

ML Performance

FP16 (Half Precision)

34.1 TFLOPS 653.7 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

34.1 TFLOPS 81.72 TFLOPS

FP64 (Double Precision)

0.5328 TFLOPS 81.72 TFLOPS

CUDA Cores

10,240 19,456

RT Cores

80 No

Architecture & Compatibility

GPU Architecture

Ampere CDNA 3.0

SM (Streaming Multiprocessor)

80 No

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

8.6 No

Clocks & Performance

Base Clock

1,365 1,000

Boost Clock

1,665 2,100

Memory Clock

1,188 2,525

Power Consumption

TDP/TGP

🔥 -65% 350 W
1000 W

Recommended PSU

🔥 -46% 750 W
1400 W

Power Connector

3x 8-pin None

Rendering

Texture Units (TMU)

320 1,216

ROP

80 No

L2 Cache

6 MB 16 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

Triple-slot OAM Module

Release Date

May 31, 2021 Oct. 12, 2024

Display Outputs

1x HDMI 2.1
3x DisplayPort 1.4a

2x HDMI 2.1
3x DisplayPort 1.4a
No outputs

Renting is cheaper than buying