AMD Radeon Instinct MI250 vs NVIDIA T600

Comparison of AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs NVIDIA T600 with 4 GB GDDR6 and 640 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI250 outperforms NVIDIA T600 by 2,727.22% 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

NVIDIA T600

1.8

NVIDIA T600

1.8

Contents:

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

Memory

Memory Size

🔥 +3,100% 128 ГБ
4 ГБ

Memory Type

HBM2e GDDR6

Memory Bandwidth

🔥 3.28 TB/s
160.0 GB/s

Memory Bus Width

8,192 бит 128 бит

ML Performance

FP16 (Half Precision)

🔥 +10,494% 362.1 TFLOPS
3.418 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +2,548% 45.26 TFLOPS
1.709 TFLOPS

FP64 (Double Precision)

🔥 +84,657% 45.26 TFLOPS
0.053399999999999996 TFLOPS

CUDA Cores

🔥 +1,980% 13,312
640

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Turing

SM (Streaming Multiprocessor)

No
🔥 10

PCIe Version

PCIe 4.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

No 7.5

Clocks & Performance

Base Clock

🔥 +36% 1,000
735

Boost Clock

🔥 +27% 1,700
1,335

Memory Clock

🔥 +28% 1,600
1,250

Power Consumption

TDP/TGP

500 W
🔥 -92% 40 W

Recommended PSU

900 W
🔥 -78% 200 W

Power Connector

2x 8-pin None

Rendering

Texture Units (TMU)

🔥 +1,980% 832
40

ROP

No No

L2 Cache

🔥 16 MB
1024 KB

Benchmarks

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

63.9 tokens/s

Additional

Slots

Dual-slot Single-slot

Release Date

Nov. 8, 2021 April 12, 2021

Display Outputs

No outputs
4x mini-DisplayPort 1.4a

Renting is cheaper than buying