AMD Radeon Instinct MI250 vs NVIDIA TITAN X Pascal

Comparison of AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs NVIDIA TITAN X Pascal with 12 GB GDDR5X and 3,584 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI250 outperforms NVIDIA TITAN X Pascal by 519.85% 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 TITAN X Pascal

8.2

NVIDIA TITAN X Pascal

8.2

Contents:

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

Memory

Memory Size

🔥 +967% 128 ГБ
12 ГБ

Memory Type

HBM2e GDDR5X

Memory Bandwidth

🔥 3.28 TB/s
480.4 GB/s

Memory Bus Width

8,192 бит 384 бит

ML Performance

FP16 (Half Precision)

🔥 +111% 362.1 TFLOPS
171.5 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +313% 45.26 TFLOPS
10.97 TFLOPS

FP64 (Double Precision)

🔥 +13,099% 45.26 TFLOPS
0.3429 TFLOPS

CUDA Cores

🔥 +271% 13,312
3,584

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Pascal

SM (Streaming Multiprocessor)

No 28

PCIe Version

PCIe 4.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

No 6.1

Clocks & Performance

Base Clock

🔥 1,000
1,417

Boost Clock

🔥 +11% 1,700
1,531

Memory Clock

🔥 +28% 1,600
1,251

Power Consumption

TDP/TGP

500 W
🔥 -50% 250 W

Recommended PSU

900 W
🔥 -33% 600 W

Power Connector

2x 8-pin 1x 6-pin + 1x 8-pin

Rendering

Texture Units (TMU)

🔥 +271% 832
224

ROP

No No

L2 Cache

🔥 +433% 16 MB
3 MB

Benchmarks

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

63.9 tokens/s

Additional

Slots

Dual-slot Dual-slot

Release Date

Nov. 8, 2021 Aug. 2, 2016

Display Outputs

No outputs
1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a

Renting is cheaper than buying