MINISFORUM Launches MS-S1 MAX-P495 With 192GB Memory

Oct 8, 2026
The compact workstation runs large AI models locally using an AMD Ryzen AI Max+ PRO 495 processor and up to 192GB of unified memory.

MINISFORUM launches the MS-S1 MAX-P495 workstation it unveiled at IFA 2026, the company announced in a press release. The system is available for preorder with 192GB of unified memory and a 2TB SSD for $7,399, with shipping expected to begin in mid October.

The workstation uses a AMD Ryzen AI Max+ PRO 495 processor with 16 CPU cores, 32 threads and Radeon 8065S graphics. It provides up to 55 TOPS from its neural processing unit and 131 TOPS of total AI compute. Up to 160GB of the unified memory can be allocated as graphics memory.

MINISFORUM says one system ran the 284 billion parameter DeepSeek V4 Flash model at about 12 tokens per second. Two connected units ran Qwen3.5 with 397 billion parameters at about 16 tokens per second, while a four system configuration ran a quantized DeepSeek R1 model with 671 billion parameters. The workstation also supports installation in a 2U rack.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.