Intel Arc B770 vs NVIDIA B200

Comparison Intel Arc B770 with 16 GB GDDR6 and 4,096 cores vs NVIDIA B200 with 90 GB HBM3e and 18,944 cores.

Loading...

Performance Rating

NVIDIA B200 outperforms Intel Arc B770 by 472.76% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

Intel Arc B770

11.5

Intel Arc B770

11.5
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA B200

65.8

NVIDIA B200

65.8

Expert Comparison

Intel Arc B770 лучше по цене и энергоэффективности, подходит для средней графики и офисных задач. NVIDIA B200 с гораздо большей пропускной способностью и вычислительной мощностью (74.45 TFLOPS против 19.66) идеально подходит для высокопроизводительных задач, таких как машинное обучение и интенсивные вычисления, но потребляет значительно больше энергии.

Contents:

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

Memory

Memory Size

16 GB
🔥 +462% 90 ГБ ×2 (180 ГБ)

Memory Type

GDDR6 HBM3e

Memory Bandwidth

512.0 GB/s
🔥 4.10 TB/s ×2 (8.2 TB/s)

Memory Bus Width

256 бит 4,096 бит ×2 (8192 бит)

ML Performance

FP16 (Half Precision)

🔥 +3,201% 39.32 TFLOPS
1.1912 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

19.66 TFLOPS
🔥 +279% 74.45 TFLOPS

FP64 (Double Precision)

2.458 TFLOPS
🔥 +1,414% 37.22 TFLOPS

CUDA Cores

4,096
🔥 +362% 18,944 ×2 (37888)

RT Cores

🔥 32
No

Architecture & Compatibility

GPU Architecture

Xe2-HPG Blackwell

SM (Streaming Multiprocessor)

No
🔥 148

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No 10.0

CUDA Toolkit (first supported)

v12

CUDA Toolkit status

Supported Supported

Clocks & Performance

Base Clock

🔥 +200% 2,100
700

Boost Clock

🔥 +22% 2,400
1,965

Memory Clock

2,000 2,000

Power Consumption

Recommended PSU

🔥 -61% 550 W
1400 W

Power Connector

1x 6-pin + 1x 8-pin No

TDP/TGP

🔥 -78% 225 W
1000 W

Rendering

Texture Units (TMU)

256
🔥 +131% 592 ×2 (1184)

ROP

🔥 32
No

L2 Cache

16 MB
🔥 +212% 50 MB

Benchmarks

llama.cpp, llama 7B Q4_0

315.9 tokens/s

Additional

Slots

Dual-slot
🔥 SXM Module

Release Date

March 12, 2026 March 13, 2024

Display Outputs

1x HDMI 2.1a
3x DisplayPort 2.1
No outputs

Renting is cheaper than buying