AMD Radeon Instinct MI250 vs ONDA RTX 3050 AEGIS

Comparison of AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs ONDA RTX 3050 AEGIS with 8 GB GDDR6 and 2,560 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI250 outperforms ONDA RTX 3050 AEGIS by 849.44% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI250

50.9

AMD Radeon Instinct MI250

50.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

ONDA RTX 3050 AEGIS

5.4

ONDA RTX 3050 AEGIS

5.4

Contents:

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

Memory

Memory Size

🔥 +1,500% 128 ГБ
8 ГБ

Memory Type

HBM2e GDDR6

Memory Bandwidth

🔥 3.28 TB/s
224.0 GB/s

Memory Bus Width

8,192 бит 128 бит

ML Performance

FP16 (Half Precision)

🔥 +3,880% 362.1 TFLOPS
9.098 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +397% 45.26 TFLOPS
9.098 TFLOPS

FP64 (Double Precision)

🔥 +31,728% 45.26 TFLOPS
0.1422 TFLOPS

CUDA Cores

🔥 +420% 13,312
2,560

RT Cores

No
🔥 20

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Ampere

SM (Streaming Multiprocessor)

No
🔥 20

PCIe Version

PCIe 4.0 x16 PCIe 4.0 x8

ML Software Support

CUDA Version

No 8.6

Clocks & Performance

Base Clock

1,000
🔥 +55% 1,552

Boost Clock

1,700
🔥 +5% 1,777

Memory Clock

1,600
🔥 +9% 1,750

Power Consumption

TDP/TGP

500 W
🔥 -74% 130 W

Recommended PSU

900 W
🔥 -67% 300 W

Power Connector

2x 8-pin 1x 8-pin

Rendering

Texture Units (TMU)

🔥 +940% 832
80

ROP

No
🔥 20

L2 Cache

16 MB
🔥 2 MB

Benchmarks

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

63.9 tokens/s

Additional

Slots

Dual-slot Dual-slot

Release Date

Nov. 8, 2021 Jan. 4, 2022

Display Outputs

No outputs
1x HDMI 2.1
3x DisplayPort 1.4a

Renting is cheaper than buying