AMD Radeon Instinct MI250 vs NVIDIA TITAN Ada

Comparison of AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs NVIDIA TITAN Ada with 48 GB GDDR6X and 18,432 cores.

Loading...

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 Ada

NVIDIA TITAN Ada

Contents:

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

Memory

Memory Size

🔥 +167% 128 ГБ
48 GB

Memory Type

HBM2e GDDR6X

Memory Bandwidth

🔥 +185% 3.28 TB/s
1.15 TB/s

Memory Bus Width

8,192 бит 384 бит

ML Performance

FP16 (Half Precision)

🔥 +290% 362.1 TFLOPS
92.9 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 45.26 TFLOPS
92.9 TFLOPS

FP64 (Double Precision)

🔥 +3,018% 45.26 TFLOPS
1.4515 TFLOPS

CUDA Cores

🔥 13,312
18,432

RT Cores

No 144

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Ada Lovelace

SM (Streaming Multiprocessor)

No 144

PCIe Version

PCIe 4.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No 8.9

Clocks & Performance

Base Clock

🔥 1,000
2,235

Boost Clock

🔥 1,700
2,520

Memory Clock

🔥 +7% 1,600
1,500

Power Consumption

TDP/TGP

🔥 -38% 500 W
800 W

Recommended PSU

🔥 -25% 900 W
1200 W

Power Connector

2x 8-pin 2x 16-pin

Rendering

Texture Units (TMU)

🔥 +44% 832
576

ROP

No 144

L2 Cache

🔥 16 MB
96 MB

Benchmarks

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

63.9 tokens/s

Additional

Slots

Dual-slot Quad-slot

Release Date

Nov. 8, 2021 No

Display Outputs

No outputs
1x HDMI 2.1
3x DisplayPort 1.4a

Renting is cheaper than buying