AMD Radeon Instinct MI250 vs Gainward RTX 4070 Ti SUPER Phantom

Comparison of AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs Gainward RTX 4070 Ti SUPER Phantom with 16 GB GDDR6X and 8,448 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

AMD Radeon Instinct MI250

AMD Radeon Instinct MI250

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

Gainward RTX 4070 Ti SUPER Phantom

18.9

Gainward RTX 4070 Ti SUPER Phantom

18.9

Contents:

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

Memory

Memory Size

128 GB
🔥 16 ГБ

Memory Type

HBM2e GDDR6X

Memory Bandwidth

3.28 TB/s 672.3 GB/s

Memory Bus Width

8,192 бит 256 бит

ML Performance

FP16 (Half Precision)

362.1 TFLOPS
🔥 44.1 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

45.26 TFLOPS
🔥 44.1 TFLOPS

FP64 (Double Precision)

45.26 TFLOPS
🔥 0.689 TFLOPS

CUDA Cores

13,312
🔥 8,448

RT Cores

No
🔥 66

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Ada Lovelace

SM (Streaming Multiprocessor)

No
🔥 66

PCIe Version

PCIe 4.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No 8.9

Clocks & Performance

Base Clock

1,000
🔥 +134% 2,340

Boost Clock

1,700
🔥 +54% 2,610

Memory Clock

1,600
🔥 1,313

Power Consumption

TDP/TGP

500 W
🔥 -43% 285 W

Recommended PSU

900 W
🔥 -33% 600 W

Power Connector

2x 8-pin 1x 16-pin

Rendering

Texture Units (TMU)

832
🔥 264

ROP

No
🔥 66

L2 Cache

16 MB
🔥 +200% 48 MB

Benchmarks

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

63.9 tokens/s

Additional

Slots

Dual-slot Triple-slot

Release Date

Nov. 8, 2021 Jan. 8, 2024

Display Outputs

No outputs
1x HDMI 2.1
3x DisplayPort 1.4a

Renting is cheaper than buying