Skip to product information
MINISFORUM US
MINISFORUM MS-S1 Max
Sale price
$2,599.00
Regular price
$3,249.00
Copy
For bulk discount inquiries, please contact elsa@minisforum.com
- Equipped with AMD Ryzen™ AI Max+ 395
- AI Performance · Up to 126 TOPS
- LPDDR5x-8000MT/s | Up To 128GB
- USB4 V2 & Dual 10GbE & WIFI 7
- PCIE x16 Expansion | Support 2U Rack
Please note: The 64GB memory chips on this model are soldered to the motherboard. User upgrade to 128GB is not possible.
Payment Methods:
Trusted Delivery:
Compare Specs
Powerful Intelligence
Enabling Future Possibilities
Enabling Future Possibilities
All-in-One
AMD Ryzen™ AI Max+ 395
AMD Radeon 8060S Graphics
AMD Radeon 8060S Graphics
Built for AI Large Models
All-Scenario AI Computing
Up to 126 TOPS
Run 128B+ LLMs Locally
Run 128B+ LLMs Locally
UMA
Unified Memory Architecture
Up to 128GB LPDDR5x-8000MT/s
Eliminates VRAM Bottlenecks, Low-Latency Speed
Eliminates VRAM Bottlenecks, Low-Latency Speed
Rack Clusters
Unleash Scalable AI Power
From dual-unit cluster to 2U rack
Heat Dissipation
Top-tier Thermal Solution
Copper Base, 6 Heat Pipes
Dual Fans & Phase-Change Cooling
160W Peak, 130W Sustaine
Dual Fans & Phase-Change Cooling
160W Peak, 130W Sustaine
Interface
Comprehensive I/O
USB4 V2, Dual 10GbE & Wi-Fi 7
PCIe 4.0 x4
PCIe Expansion
Full-length x16 Slot for Versatile Expansion Cards Support
Global Certified PSU
Reliable Power-Supply
Built-in 320W PSU with CCC, FCC, UL, CE, UKCA and More Global Certifications
Design
Slide-Out Structure Design
Slide-out Chassis for Easy Upgrade & Maintenance
Your Best Computing Partner
Your Best Computing Partner
AI Enthusiasts
Geeks & Power Users
Creative Professionals
Enterprise / Industry / Education
AI Enthusiasts
MS-S1 MAX empowers AI enthusiasts to run large language models locally, build AI applications, and experience real-time, low-latency inference.
Third-party trademarks are property of their owners.
Software compatibility is not supported by Minisforum.
Geeks & Power Users
MS-S1 MAX enables geeks and power users to test cutting-edge AI frameworks, deploy multimodal models, and harness massive memory and computing power.
Third-party trademarks are property of their owners.Software compatibility is not supported by Minisforum.
Creative Professionals
MS-S1 MAX is designed for creative professionals, accelerating video editing, 3D rendering, AI art, and audio production through 128GB UMA memory and multi-display output.
Third-party trademarks are property of their owners.Software compatibility is not supported by Minisforum.
University AI Education
Run AI demos and training locally with high compute power, compact and portable.
Professional AI Training
Training centers run local models to cut cloud costs and ensure data security.
Regional Security Monitoring
On-prem AI analyzes video streams in real time with low latency and high security.
Marketing & Advertising Teams
Accelerate ad modeling and campaign iteration with AI compute.
SME Intelligent Workflows
Build private knowledge bases and agents for cloud-like intelligence at low cost.
Ultimate Computing for
Next-Gen AI
Ultimate Computing for Next-Gen AI
APU
126 TOPS
UMA
Peak Power
Multi-Model Support
Powered by AMD Ryzen™ AI Max+ 395, integrating Zen5 CPU, RDNA 3.5 GPU, and a next-gen NPU. With 16 cores and 32 threads delivering RTX 4070 Laptop-level GPU performance plus 50 TOPS NPU acceleration, it achieves more efficient AI inference.
Delivers up to 126 TOPS, with AI performance tested at 2.2× that of RTX 4090, effortlessly handling everything from LLMs to multimodal generation.
Supports up to 128GB LPDDR5x-8000MT/s quad-channel memory, eliminating traditional VRAM bottlenecks for low-latency, high-speed data transfer.
160W peak power, 130W sustained load, ensuring long-term high-intensity computing stability.
Compatible with diverse large models and precision levels, delivering fast and stable output.
From Desktop to Rack
Building an Efficient Computing Hub
From Desktop to Rack Building an Efficient Computing Hub
Dual-unit 235B Cluster
2U Rack · Four-Unit Cluster Scalability
Two MS-S1 MAX units can be easily clustered together, flexibly scaling computing power for personal research or small studio workloads. In real-world tests, a dual-unit cluster runs the 235B Q4 large model locally, delivering an output speed of 10.87 tok/sec.
Supports 2U rack deployment, where multiple MS-S1 MAX units can be cascaded into a distributed cluster, creating an efficient AI computing hub for enterprises and research teams.
In real-world testing, a four-unit cluster successfully ran the DeepSeek-R1 671B Q4 large model (380GB, Q4_0 quantization), marking a breakthrough in local large-model computation for compact AI workstations.
Top-tier Thermal Solution for
Stable Computing Power
Top-tier Thermal Solution for Stable Computing Power
Aluminum Body
Solid Copper
Dual Fans
PCM Cooling
Peak 160W
Aerospace-Grade Aluminum Chassis
Aluminum chassis integrates a diamond-matrix grill for robust durability and efficient airflow, achieving a perfect synergy of superior cooling and tech-inspired aesthetics.
Copper Base & 6 Heat-Pipe Array
The pure copper heat spreader instantly captures CPU heat, which is then efficiently distributed and dissipated by the six high-performance heat pipes for dramatically lower temperatures.
Powerful Dual Turbine Fans
They generate a powerful, focused airflow to efficiently exhaust heat to prevent heat buildup.
Advanced Phase Change Material
It liquefies under heat to perfectly fill microscopic imperfections between the chip and cooler, resulting in superior thermal transfer compared to standard pastes.
130W Stable / 160W Peak PPT
With a robust 130W stable PPT and 160W Fast PPT, our cooling system confidently handles intense workloads, translating extreme power into unwavering performance, not thermal throttling.
Global-Certificatied Safe and
Efficient Power
Global-Certificatied Safe and Efficient Power
Built-in 320W high-efficiency PSU with CCC, FCC, UL, CE, UKCA and more global certifications, ensuring stable and reliable power delivery.
Engineered for Versatile Workflows
Smart Voice
Precise Recognition
Built-in AI noise-cancelling mic supports mainstream AI models, capturing voice commands with clarity.
Multiple Modes
From Desktop to Rack
Four switchable modes-Performance, Balance, Quiet, and Rack-flexibly adapt from personal desktops to enterprise clusters.
Easy Upgrade
Slide-Out Structure Design
Slide-out chassis with integrated board tray for effortless upgrades and maintenance.
Cluster Control
One-Click Start / Stop
With reserved cascade power-on header, multiple units can be powered on/off together for effortless cluster management.
Versatile Usage
Vertical or Horizontal
Supports both vertical desktop setup and horizontal rack deployment, adaptable for personal and enterprise use.
Full Connectivity and Expansion
Full Connectivity and Expansion
I/O Ports
Dual M.2 Slots
PCIe x16
Front
Rear
1.Power Button
2. DMIC ×2
3. USB 3.2 Gen2 (10Gbps)
4. USB4 ×2 (40Gbps, Alt DP2.0, PD out 15W)
5. 3.5mm Audio Combo Jack
6.HDMI™ 2.1 FRL (Up to 8K@60Hz/4K@120Hz)
7. USB 2.0 ×2
8. USB4 V2 ×2 (80Gbps, Alt DP2.0, PD out 15W)
9. USB 3.2 Gen2 (10Gbps)
10. 10GbE LAN x2 (RJ45, Realtek RTL8127)
11. Anti-Theft Lock Hole
12. Reset Hole (Clear CMOS)
13. AC INPUT
1.Power Button
2. DMIC ×2
3. USB 3.2 Gen2 (10Gbps)
4. USB4 ×2 (40Gbps, Alt DP2.0, PD out 15W)
5. 3.5mm Audio Combo Jack
6.HDMI™ 2.1 FRL (Up to 8K@60Hz/4K@120Hz)
7. USB 2.0 ×2
8. USB4 V2 ×2 (80Gbps, Alt DP2.0, PD out 15W)
9. USB 3.2 Gen2 (10Gbps)
10. 10GbE LAN x2 (RJ45, Realtek RTL8127)
11. Anti-Theft Lock Hole
12. Reset Hole (Clear CMOS)
13. AC INPUT
Storage & Expansion
Easy Upgrade
Dual M.2 slots (PCIe 4.0 x4 + x1) support up to 8+8=16TB with RAID0/1, integrated slide-out board design enables effortless upgrades and maintenance.
8TB
Per Slot Maximum SSD Capacity
RAID 0/1
Flexible RAID Support
Storage & Expansion
Easy Upgrade
Dual M.2 slots (PCIe 4.0 x4 + x1) support up to 8+8=16TB with RAID0/1, integrated slide-out board design enables effortless upgrades and maintenance.
8TB
Per Slot Maximum SSD Capacity
RAID 0/1
Flexible RAID Support
Flexible Customization
Full-Length Expansion
Full-length PCIe x16 slot supports industry-specific expansion needs.
PCIe x16
Supports Full-length Cards
PCIe 4.0 x4
High-speed Expansion
Flexible Customization
Full-Length Expansion
Full-length PCIe x16 slot supports industry-specific expansion needs.
PCIe x16
Supports Full-length Cards
PCIe 4.0 x4
High-speed Expansion
MS-S1 MAX Specification
CPU
AMD Ryzen™ AI Max+ 395
16 Cores, 32 Threads
Max Clock: 5.1 GHz
TDP
Performance Mode: 130W
Balanced Mode: 95W
Quiet Mode: 60W
GPU
Radeon 8060S Graphics (Internal)
GPU Cores: 40
GPU Clock: 2900 MHz
AI Engine Performance
AMD Ryzen™ AI
NPU Computing Power: Up to 50 TOPS
Total Computing Power: Up to 126 TOPS
RAM
LPDDR5x-256Bit
Max frequency support: 8000MHz
Max capacity support: 128GB
SSD
1× M.2 2280 NVMe SSD slot
(supports up to 8TB, PCIe 4.0 ×4)
1× M.2 2280 NVMe SSD slot
(supports up to 8TB, PCIe 4.0 ×1)
Heat Dissipation
6 Heat Pipes & Phase Change Material
Dual Turbine Fans
Max CPU Fan Speed: 3600 RPM
Wireless Connectivity
Wi-Fi 7 | Bluetooth® 5.4
Ethernet Controller
2× 10GbE LAN (RJ45)
Video Output
1× HDMI (up to 8K@60Hz/4K@120Hz)
2× USB4 (up to 8K@60Hz/4K@120Hz)
2× USB4 V2 (up to 8K@60Hz/4K@120Hz)
Audio Output
HDMI ×1
3.5mm Audio Combo Jack (TRRS) ×1
Audio Input
DMIC ×2
3.5mm Audio Combo Jack (TRRS) ×1
I/O Ports (Front)
2× USB4 (40Gbps, Alt DP 2.0, PD out 15W)
1× USB 3.2 Gen2 (10Gbps)
1× 3.5mm Audio Combo Jack (TRRS)
2× DMIC
I/O Ports (Rear)
1× 10GbE LAN (RJ45, Realtek RTL8127)
1× 10GbE LAN (RJ45, Realtek RTL8127)
2× USB 3.2 Gen2 (10Gbps)
2× USB 2.0
2× USB4 V2 (80Gbps, Alt DP2.0, PD out 15W)
1× HDMI 2.1 FRL (Up to 8K@60Hz/4K@120Hz)
I/O Ports (Internal)
PCIe ×16 slot (PCIe 4.0 ×4)
Button/Hole
1× Power Button (with LED)
1× BIOS Reset Hole
Pre-installed OS
OS Support
OS Support
Windows 11 Pro
Windows 11 24H2 Pro / Home
Power
AC INPUT
(100-240V ~6A 50-60Hz, Internel-DC 12V/26.6A, 320W MAX)
VESA Mount & Dimensions
100-178.5mm
222.1 × 206.3 × 77.1 mm
Weight
2.8 kg