Intel Data Center GPU Max NEXT vs XFX XFX QICKSILVER MagAir RX 7800 XT

Comparison Intel Data Center GPU Max NEXT with 128 GB HBM2e and 20,480 cores vs XFX XFX QICKSILVER MagAir RX 7800 XT with 16 GB GDDR6 and 3,840 cores.

Loading...

Performance Rating

Intel Data Center GPU Max NEXT outperforms XFX XFX QICKSILVER MagAir RX 7800 XT by 265.41% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

Intel Data Center GPU Max NEXT

62.1

Intel Data Center GPU Max NEXT

62.1
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

XFX XFX QICKSILVER MagAir RX 7800 XT

17.0

XFX XFX QICKSILVER MagAir RX 7800 XT

17.0

Expert Comparison

Intel Data Center GPU Max NEXT явно выигрывает по многим параметрам: имеет больше ядер, большую память и пропускную способность. Подходит для вычислительных задач и больших данных. XFX QICKSILVER MagAir RX 7800 XT более мощный по отношению к потребляемой энергии, но значительно уступает по характеристикам для обработки больших объемов данных или вычислительной мощности.

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 GDDR6

Memory Bandwidth

🔥 3.21 TB/s
624.1 GB/s

Memory Bus Width

8,192 бит 256 бит

ML Performance

FP16 (Half Precision)

65.54 TFLOPS
🔥 +14% 74.65 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

65.54 TFLOPS
🔥 37.32 TFLOPS

FP64 (Double Precision)

65.54 TFLOPS
🔥 +1,778,966% 1,166,000.0 TFLOPS

CUDA Cores

20,480
🔥 3,840

RT Cores

160
🔥 60

Architecture & Compatibility

GPU Architecture

Generation 12.5 RDNA 3.0

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x16

ML Software Support

CUDA Version

No No

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

900
🔥 +44% 1,295

Boost Clock

1,600
🔥 +52% 2,430

Memory Clock

1,565
🔥 +56% 2,438

Power Consumption

Recommended PSU

1200 W
🔥 -50% 600 W

Power Connector

8-pin EPS 2x 8-pin

TDP/TGP

800 W
🔥 -67% 263 W

Rendering

Texture Units (TMU)

1,280
🔥 240

ROP

160
🔥 60

L2 Cache

408 MB
🔥 4 MB

Benchmarks

MLPerf, llama2-70b-99.9 (UINT4)

527.5 tokens/s

MLPerf, llama3.1-8b (UINT4)

1 337 tokens/s

MLPerf, llama3.1-8b-edge (UINT4)

1 652 tokens/s

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

8.21 tokens/s

Additional

Slots

OAM Module Dual-slot

Release Date

No June 18, 2024

Display Outputs

No outputs
1x HDMI 2.1a
3x DisplayPort 2.1

Renting is cheaper than buying