Skip to product information

Free Shipping

Free Shipping

Free RMA return

Free RMA return

0% APR plan

0% APR plan

2 Years Warranty

2 Years Warranty

30-Day Money-Back Guarantee

30-Day Money-Back Guarantee

AI NAS N5 MAX

Sale price  €2.719,00 Regular price  €3.399,00

Note:
The model with 128GB LPDDR5 RAM + 128GB SSD is expected to ship in mid-September!

  • AMD Ryzen™ AI Max+ 395,16C/32T
  • Up to 126 TOPS Local AI Performance
  • 5-Bay HDD + 5-Bay SSD | Up To 200TB
  • 128GB LPDDR5X 256-bit Unified Memory
  • Dual 10GbE LAN | MinisCloud OS Pre-installed
  • One-click Docker Installation | 2× USB4 v2 Ports
CPU:

AMD Ryzen™ AI Max+ 395

Type:

64GB LPDDR5 RAM+128GB SSD

×
Brand Shop Exclusive Benefits
  • Online Instant Service
  • 3-Year Extended Warranty
  • Gift Redemption with Points
Deliverable Areas

Can be delivered for free to:

  • EU countries: Czech Republic, Denmark, Austria, Belgium, Bulgaria, Croatia, Estonia, Finland, France, Germany, Greece, Ireland, Italy, Latvia, Lithuania, Luxembourg, Netherlands, Poland, Portugal, Romania, Slovakia, Slovenia, Spain, Sweden, Hungary.
  • Non-EU countries: Switzerland, Albania, Belarus, North Macedonia, Iceland, Bosnia and Herzegovina, Vatican City, Liechtenstein, Monaco, Norway, San Marino.
Delivery Timeliness
  • DE Warehouse: 5-7 business days
  • Hong Kong Warehouse: 7-10 business days
  • Refurbished Devices: 5-7 business days
  • Pre-sale Products: 5-7 business days after warehouse arrival
Repair Services

Provides free repair and after-sales services for products that are within the warranty period. For more details, please contact the customer service team.

Insurance Services

Minisforum provides two types of protection for sold products:

  • 1. Shipping Protection includes: Loss and damage in transit, Theft/Porch Piracy, Mis-delivery by courier, USD$5 compensation for delay Smooth Claims
  • 2. Product Protection Plan:Customers can choose a 1-year, 2-year, or 3-year insurance plan tailored to their needs. This plan covers accidental damage occurring during normal product use and extends the original manufacturer's warranty with identical coverage terms after its expiration. Different durations are subject to varying premium rates.

Payment Methods

Visa Mastercard American Express PayPalDiscoverJCBDiners ClubUnion PayGoogle Pay Apple Pay Visa ElectronCartes Bancaires KlarnaiDEAL WeroTrustly EPS BancontactSkrill Digital WalletBancomat Billink

Trusted Delivery

Free Shipping

Free Shipping

Free RMA Return

Free RMA Return

0% APR Plan

0% APR Plan

Up To 3 Years Extended Warranty

Up To 3 Years Extended Warranty

30-Day Money-Back Guarantee

30-Day Money-Back Guarantee
Sale price  €2.719,00 Regular price  €3.399,00 Save €680,00
Buy Now

Your Personal Al Revolution

Your Data

Your AI, Total Control

One System, One WorkflowOne System, One Workflow
Your Data, Your RulesYour Data, Your Rules
Built For Today, Ready For TomorrowBuilt For Today, Ready For Tomorrow
Extreme Local AI

AMD Ryzen AI Max+ 395, Radeon™ 8060S, Up To 126 TOPS, And A High-Bandwidth LPDDR5x Architecture Bring Truly Usable High-Performance Local AI Into A 5-Bay AI NAS.

    • Extreme Compute Foundation: Ryzen AI Max+ 395 | Radeon™ 8060S | Up To 126 TOPS
    • High-Bandwidth Memory: LPDDR5x Accelerates Model Access, Multitasking, And High-Frequency Workloads
    • Local AI Entry Point: MinisOpenClaw + One-Click Permission Control For Faster, Safer AI Access

    *MinisClaw uses Qwen3.6-35B as its default model. 120B-class model results shown above are based on local benchmark testing and do not represent the default MinisClaw model.

One System, One Workflow
Your Data, Your Rules
Built For Today, Ready For Tomorrow

AMD Ryzen AI Max+ 395, Radeon™ 8060S, Up To 126 TOPS, And A High-Bandwidth LPDDR5x Architecture Bring Truly Usable High-Performance Local AI Into A 5-Bay AI NAS.

    • Extreme Compute Foundation: Ryzen AI Max+ 395 | Radeon™ 8060S | Up To 126 TOPS
    • High-Bandwidth Memory: LPDDR5x Accelerates Model Access, Multitasking, And High-Frequency Workloads
    • Local AI Entry Point: MinisOpenClaw + One-Click Permission Control For Faster, Safer AI Access

    *MinisClaw uses Qwen3.6-35B as its default model. 120B-class model results shown above are based on local benchmark testing and do not represent the default MinisClaw model.

120B-Class AI

Running Local

128GB Unified Memory Gives N5 MAX The Headroom To Run 120B-Class Open Models Locally, While Ryzen AI Max+ 395 And Radeon 8060S Keep Reasoning, Coding, And Agent Workflows Moving At Responsive Speeds.

gpt-oss-120b

120B-Class Open Reasoning, Running Local

59.30 tokens/s
Text Generation
668.79 tokens/s
Prompt Processing
59.03 GB
MXFP4

Qwen3.5-122B-A10B

122B Multimodal Intelligence, On Device

31.76 tokens/s
Text Generation
317.58 tokens/s
Prompt Processing
69.11 GB
Q4_K_M

gpt-oss-20b

Fast Local Reasoning for Everyday Agents

83.09 tokens/s
Text Generation
1,575.75 tokens/s
Prompt Processing
11.28 GB
MXFP4

Gemma 4 26B-A4B

Efficient Intelligence, Responsive by Design

70.33 tokens/s
Text Generation
1,200.58 tokens/s
Prompt Processing
15.64 GB
Q4_K_M

*Benchmark Note
Internal test results based on GGUF quantized models using llama.cpp llama-bench, with 99 GPU layers and Flash Attention enabled. PP512 measures prompt-processing throughput; TG128 measures text-generation speed. Actual performance may vary by model version, quantization, context length, system configuration, and software environment.

Strix Halo Power

Powered by Ryzen AI Max+ 395 on the Strix Halo platform, N5 MAX brings true high-performance local AI into a 5-bay NAS form factor.
*MinisClaw uses Qwen3.6-35B as its default model. 120B-class model results shown above are based on local benchmark testing and do not represent the default MinisClaw model.

Ryzen AI Max+ 395 Inside: A 16-core, 32-thread AI platform built to keep local AI responsive under real workloads.

Radeon™ 8060S Graphics: Strong graphics capability for AI-assisted creation, visual workloads, and generation-heavy workflows.

120B-Class Local Model Ready: The 128GB configuration brings models such as gpt-oss-120b and Qwen3.5-122B-A10B into practical local workflows.

Bandwidth Beats Bulk

LPDDR5x 8533MT/S On A 256-Bit Bus, Gives AI Agents The Speed, Bandwidth, And Stability They Need Under Real Workloads.

LPDDR5x
Max 8533MT/s

Top-tier consumer-platform memory speed for faster model access and AI calls.

256-bit
Memory Bus

Wider bandwidth keeps compute, graphics, and data-heavy AI workloads better fed.

Up to 128GB
Unified Memory

More room for 120B-class local models, while 8533MT/s speed and a 256-bit bus keep data moving fast.

Make Massive Storage Move

5 × HDD Bays & 5 × M.2 SSD Slots Combine Mass Capacity With SSD Acceleration, Giving Large HDD
Arrays The Feel Of A Much Faster Working System.

5× HDD Bays

Built for archives, project libraries, media
assets, private data, and long-term storage

Built for archives, project libraries, media assets, private data, and long-term storage

5× M.2 NVMe Slots

Use SSDs for cache, hot data, models,
project files, and HDD array acceleration

Use SSDs for cache, hot data, models, project files, and HDD array acceleration

Up to 200TB Capacity

Keep models, assets, cache, archives, and
output inside one unified AI NAS platform

Keep models, assets, cache, archives, and output inside one unified AI NAS platform

Multiple RAID Modes For Data Security

Multiple RAID Modes For Data Security

Supports RAID0, RAID1, RAID5/RAIDZ1, RAID6/RAIDZ2 And Mixed Drive Strategies For Hot Data And Cold Backup, Speeding Reads And Cutting Storage Costs.

RAID 0

Multi-Drive Accelerate

RAID 1

Secure and Stable

RAID 5

Balanced Performance

RAID 6

Maximum Security

Move Data Like You Mean It

Dual 10GbE And USB4 V2 At 80Gbps Give N5 MAX The Bandwidth To Move Data, Expand Storage, And Connect High-Performance AI Workflows.

Dual 10GbE

Built for fast team access, large-file movement,
and high-throughput local workflows

Built for fast team access, large-file movement, and high-throughput local workflows

2× USB4 v2 80Gbps

Expand with high-performance storage
enclosures or bridge into Thunderbolt-class workflows

Expand with high-performance storage enclosures or bridge into Thunderbolt-class workflows

USB4 + USB 3.2 Gen2

Fast front access for displays, devices,
and everyday expansion

Fast front access for displays, devices, and everyday expansion

HDMI™ 2.1 FRL

Up to 8K@60Hz: Direct high-resolution output for
creators, monitoring, and multi-display workflows

Up to 8K@60Hz: Direct high-resolution output for creators, monitoring, and multi-display workflows

Slide. Swap. Upgrade

A Slide-Out Motherboard Bay And Built-In Power Supply Turn High-End Hardware Into A Platform That Is Easier To Service And Cleaner To Deploy.

Slide-Out Motherboard Bay

Easier Access For Servicing, Upgrades, And Advanced Internal Operations.

Internal USB 3.2 Gen2

Adds Clean Internal Expansion While Keeping High-Speed Storage Slots Focused On Real Workloads.

Built-In Power

Cleaner Desk

A built-in 250W power supply keeps the setup cleaner while powering a serious AI NAS platform.

Built-In 250W

No Bulky External Power Brick, Just A
Cleaner Setup And A More Complete System.

No Bulky External Power Brick, Just A
Cleaner Setup And A More Complete System.

Saves Desktop Space

A Cleaner Power Design Makes N5 MAX Easier To Place In
Studios, Offices, And Home Workspaces.

A Cleaner Power Design Makes N5 MAX Easier To Place In
Studios, Offices, And Home Workspaces.

Built Flagship Platform

Designed To Support High-Performance Compute, Hybrid
Storage, And High-Speed I/O In One Box.

Designed To Support High-Performance Compute, Hybrid
Storage, And High-Speed I/O In One Box.

Stay Cool. Stay Fast

Effortless On Every Platform

Powered By Smart Services

MinisCloud OS: Your All-In-One Smart Platform
Seamlessly Supports Windows, MacOS, IOS, And Android With Zero Learning Curve.
Built-In Features Include ZFS Snapshots, LZ4 Compression, Multi-User Isolation, Docker Apps, AI Photo Albums, And One-Click Remote Access-Fully Managed, Ready To Use.

Windows

Windows

MacOS

MacOS

iOS

iOS

Android

Android

Web (Coming soon)

Web (Coming soon)

*MinisCloud OS Beta Version Actively Updated

MinisOpenClaw
Your Local AI Agent NAS

Transform Your NAS Into A Private AI System - Understand Content, Answer Questions, AndStreamline Workflows, Entirely On-Device.

ZFS snapshots effortless backups to keep your data safe

Built-in enterprise ZFS file system safeguards your data at every level:
Automatic integrity checks prevent data corruption;
Instant rollback to any point in time with snapshot management for guaranteed data recovery;
Supports RAID 0/1/5/6 with flexible storage strategies, balancing performance and security.

Ultra-Fast Compression
Maximum Storage Efficiency

MinisCloud integrates an LZ4 lossless compression engine, delivering single-core compression speeds exceeding 500 MB/s and decompression speeds up to several GB/s, effortlessly handling large file transfers and backups.
Whether for ZFS snapshots, remote file sharing, or data archiving, enjoy enterprise-grade compression performance while effectively freeing up storage space.

Offline Account System

Privacy Protection

Fully Offline Account System

Enhanced Privacy, No cloud-stored account data—user privacy is fully protected.

All User Data is Isolated by Default

New accounts authorized instantly via QR code for secure, hassle-free access

Multiple RAID Levels

Allows for data recovery even if one hard drive fails.

Fully Offline Account System

Enhanced Privacy, No cloud-stored account data—user privacy is fully protected.

All User Data is Isolated by Default

New accounts authorized instantly via QR code for secure, hassle-free access

Multiple RAID Levels

Allows for data recovery even if one hard drive fails.

Your Data

Your Space, Your Rules

Flexible Access Control With Multi-Level Spaces Personal, Private, And Shared Spaces Are Clearly Separated-Ensuring Privacy While Enabling Smooth Collaboration.

Multi-Protocol Support

Seamless Public Network Penetration

Supports Multiple Protocols And Public Network Traversal For Easy File Access From Anywhere. Encrypted Links Enable Secure Sharing Of Internal Data, Ensuring Both Convenience And Privacy.

Lighter And Faster

Per-Account Docker Container Isolation

Supports Namespace Isolation, Allowing Each Account To Run Containers Independently With No Data Interference. One-Click Port Mapping, Accelerated Image Access, And Pre-Configured Images Enable Fast, Seamless Deployment.

One Click To Backup

Sync Across All Devices

One-Click Backup And Seamless Sync Across PC And Mac, With Files Accessible Anytime, Anywhere.

Packing List

N5 MAX

Power Cord

HDMI™ Cable

Network Cable

Drive Bay Key

Screw Set

Screw Set

User Manual

N5 MAX Specification

CPU

AMD Ryzen™ AI Max+ 395,16C/32T


Max.Turbo Frequency 5.1 GHz; TDP Up to 90W

GPU

AMD Radeon 8060S Graphics

Graphics Frequency 2900 MHz

NPU

Up to 50 TOPS

Total Up to 126 TOPS

Memory

LPDDR5x Unified Memory
Optional SKU DDR Capacity: 64 GB

Max.Speed Support 8533 MT/s;
Max. Capacity Support 64 GB

Storage
  • HDD Bays 1-5: 5 × 3.5”/2.5” SATA 3.0 (Up to 32TB each, 160TB total)
  • SSD Slot A: 1 × M.2 2280 NVMe (PCIe 4.0 x4, Up to 8TB)
  • SSD Slot B: 1 × M.2 2230 / 2280 NVMe (PCIe 4.0 x1, Up to 8TB)
  • SSD Slot C,D,E: 3 × M.2 2280 NVMe (PCIe 4.0 x1, Up to 8TB each,24TB total)
  • System Disk: 128 GB (installed in one of the SSD slots)

    Total Supported Capacity: Up to 200TB (160TB HDD + 40TB SSD)