Intel Data Center GPU Max NEXT vs NVIDIA GeForce RTX 5070 Ti SUPER

Comparison of Intel Data Center GPU Max NEXT with 128 GB HBM2e and 20,480 cores vs NVIDIA GeForce RTX 5070 Ti SUPER with 16 GB GDDR7 and 8,960 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

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

NVIDIA GeForce RTX 5070 Ti SUPER

NVIDIA GeForce RTX 5070 Ti SUPER

Contents:

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

Memory

Memory Size

128 ГБ 16 GB

Memory Type

HBM2e GDDR7

Memory Bandwidth

🔥 3.21 TB/s
896.0 GB/s

Memory Bus Width

8,192 бит 256 бит

ML Performance

FP16 (Half Precision)

65.54 TFLOPS 43.94 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

65.54 TFLOPS 43.94 TFLOPS

FP64 (Double Precision)

65.54 TFLOPS 0.6866 TFLOPS

CUDA Cores

20,480 8,960

RT Cores

160 70

Architecture & Compatibility

GPU Architecture

Generation 12.5 Blackwell 2.0

SM (Streaming Multiprocessor)

No 70

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No 12.0

Clocks & Performance

Base Clock

900 2,295

Boost Clock

1,600 2,452

Memory Clock

1,565 1,750

Power Consumption

TDP/TGP

800 W
🔥 -56% 350 W

Recommended PSU

1200 W
🔥 -38% 750 W

Power Connector

8-pin EPS 1x 16-pin

Rendering

Texture Units (TMU)

1,280 280

ROP

160 70

L2 Cache

408 MB 48 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 March 11, 2026

Display Outputs

No outputs
1x HDMI 2.1b
3x DisplayPort 2.1b

Renting is cheaper than buying