Intel Arc Pro B60 vs NVIDIA H200 SXM 141 GB

Comparison Intel Arc Pro B60 with 24 GB GDDR6 and 2,560 cores vs NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores.

Loading...

Performance Rating

NVIDIA H200 SXM 141 GB outperforms Intel Arc Pro B60 by 652.85% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

Intel Arc Pro B60

9.0

Intel Arc Pro B60

9.0
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA H200 SXM 141 GB

67.4

NVIDIA H200 SXM 141 GB

67.4

Expert Comparison

Intel Arc Pro B60 лучше по энергоэффективности и цене за производительность (GPI 8.9 против 67.4 у NVIDIA H200), но значительно уступает по количеству ядер и памяти. NVIDIA H200 SXM с 141 ГБ HBM3e и 66.91 TFLOPS FP32 больше подходит для тяжелых вычислительных задач и AI, хотя потребляет гораздо больше энергии.

Contents:

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

Memory

Memory Size

24 GB
🔥 +488% 141 ГБ

Memory Type

GDDR6 HBM3e

Memory Bandwidth

456.0 GB/s
🔥 4.89 TB/s

Memory Bus Width

192 бит 6,144 бит

ML Performance

FP16 (Half Precision)

24.58 TFLOPS
🔥 +989% 267.6 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

12.29 TFLOPS
🔥 +444% 66.91 TFLOPS

FP64 (Double Precision)

3.072 TFLOPS
🔥 +989% 33.45 TFLOPS

CUDA Cores

2,560
🔥 +560% 16,896

RT Cores

🔥 20
No

Architecture & Compatibility

GPU Architecture

Xe2-HPG Hopper

SM (Streaming Multiprocessor)

No
🔥 132

PCIe Version

PCIe 5.0 x8 PCIe 5.0 x16

ML Software Support

CUDA Version

No 9.0

CUDA Toolkit (first supported)

v12

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

🔥 +33% 2,000
1,500

Boost Clock

🔥 +21% 2,400
1,980

Memory Clock

🔥 +49% 2,375
1,593

Power Consumption

Recommended PSU

🔥 -50% 550 W
1100 W

Power Connector

1x 8-pin 8-pin EPS

TDP/TGP

🔥 -71% 200 W
700 W

Rendering

Texture Units (TMU)

160
🔥 +230% 528

ROP

🔥 20
No

L2 Cache

4 MB
🔥 +1,150% 50 MB

Benchmarks

MLPerf, llama2-70b-99.9 (UNSET)

3 534 tokens/s

MLPerf, llama2-70b-99.9 (fp16)

3 553 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

2 444 tokens/s

MLPerf, llama3.1-405b (fp16)

40.8 tokens/s

MLPerf, llama3.1-405b (fp8)

25.3 tokens/s

MLPerf, llama3.1-8b (fp8)

5 161 tokens/s

MLPerf, deepseek-r1 (fp8)

1 113 tokens/s

MLPerf, mixtral-8x7b (fp8)

7 132 tokens/s

Additional

Slots

Dual-slot
🔥 SXM Module

Release Date

Sept. 5, 2025 Nov. 18, 2024

Display Outputs

4x mini-DisplayPort 2.1
No outputs

Renting is cheaper than buying