---
title: Atlas 800 AI Server-Ascend Community
description: The Atlas 800 inference server (Model 3000) supports up to eight Atlas 300I/V Pro cards, delivering powerful real-time inference and video analysis capabilities, and is widely used in AI inference sce
keywords: Atlas,AI,Server,Ascend,Community,Product,Features,Specifications
url: https://www.hiascend.com/en/hardware/ai-server
section: (其他)
---

# Atlas 800 AI Server-Ascend Community

URL: https://www.hiascend.com/en/hardware/ai-server
描述: The Atlas 800 inference server (Model 3000) supports up to eight Atlas 300I/V Pro cards, delivering powerful real-time inference and video analysis capabilities, and is widely used in AI inference sce
关键词: Atlas,AI,Server,Ascend,Community,Product,Features,Specifications

Atlas 650E

More Products

Project Consulting [了解详情](https://e.huawei.com/en/how-to-buy/get-price-info?source_website=MDFDSE5IUTE5NTE0NUw=)

AI Server

Designed for standard air-cooled data centers, the best choice for efficient & cost-effective AI computing

Atlas 650E

Atlas 650E

The Atlas 650E server, powered by eight 950DT NPUs, delivers up to 12.4 PFLOPS @ mxFP4. It features Huawei’s self-developed on-chip memory with up to 4.0 TB/s R/W bandwidth while supporting 16-NPU full-mesh via UnifiedBus Link 2.0 protocol. Designed for standard air-cooled data centers, it offers efficient, reliable AI computing for industries such as finance, government, healthcare, etc.

Project Consulting [了解详情](https://e.huawei.com/en/how-to-buy/get-price-info?source_website=MDFDSE5IUTE5NTE0NUw=)

Firmware and Driver

*Product images are for reference only.Please refer to the actual product.

## Product Features

MXFP4 Low-precision Inference

- Achieve industry-leading compute performance of 12.4 PFLOPS @ mxFP4
- Support HiF8 / mxFP8 / mxFP4 data formats，significantly improving quantization acceleration performance

Ultra-high Memory Bandwidth

- Deliver industry-leading memory R/W bandwidth of 4.0 TB/s
- 768 GB on-chip memory per server

Ultra-high UB Link Bandwidth

- Provide 13.4 TB/s UB Link bandwidth per server (16-NPU FM)
- Support 16-NPU UB full-mesh interconnect across 2 servers

## Atlas 650E Product Specifications

|  |  |
| --- | ---|
| Form Factor | 14U AI server |
| NPU | 8 × 950DT NPU |
| CPU | 2 × 950 CPU (up to 96 cores, 2.3GHz) |
| *AI Performance | 12.48 PFLOPS mxFP46.43 PFLOPS mxFP8/FP8/HiF83.40 PFLOPS FP16/BF16 |
| On-chip Memory | 8 × 96 GB total, 4.0 TB/s peak memory bandwidth |
| System Memory | Support 24 memory slots running at up to 6,400 MT/sSupport up to 64 GB per DDR5 RDIMM |
| Storage | 8 x 2.5 NVMe + 2 x 2.5 SATA (with RAID card configured) |
| UB Link Bandwidth | 8-NPU Server: 8 x 784 GB/s (bidirectional)16-NPU Full-mesh: 2 x 8 x 1.68 TB/s (bidirectional) |
| Networking | UBoE: Providing 400 Gbps per NPU (unidirectional)RoCE: Providing 400 Gbps per NPU (unidirectional) |
| Bus Type | PCIe 5.0 x 5 |
| Power Modules | 6 x 3.0 kW power supply modules, supporting hot swapping & 5+1 redundancy |
| Power Supply | 220VAC336HVDC/240HVDC |
| Cooling | Air cooling |
| Fan Modules | 30 fan modules, supporting hot swapping & N+1 redundancy |
| Power Usage | ～14.5 kW |
| Operating Temperature | 5℃～35℃（41℉～95℉） |
| Weight | 251 kg |
| Dimensions | 618.8 mm (Height) x 447mm (Width) x 920mm (Length) |

*Theoretical computing power may have a <1% error in actual testing.

*The specific configuration is subject to the actual configuration.

## Application Scenarios

For more industry solutions, check "Solutions-Industry Applications".

AI Agent

Financial Risk Control

Office Assistant

Content Review

AI Coding

AI Customer Service

Learn More [了解详情](https://www.hiascend.com/marketplace/industry)

This site uses cookies to improve your browsing experience. By continuing to browse this site, you agree to our use of cookies.View Details [了解详情](https://www.hiascend.com/en/legal/cookies)