Jack Wallen/ZDNETZDNET’s key takeaways
- The VZmore AX Max Mini PC is ideal for running local AI.
- With plenty of power to spare, the it doesn’t get bogged down.
- This machine runs local AI directly or from your LAN.
I’ve run AI on nearly every machine I own to varying degrees of success. Of course, the complexity of the task usually dictates how well it runs on any given desktop or laptop. I could open locally installed AI and ask a basic question, and that question will be answered almost immediately. Or, I could ask locally-installed AI to write an application for me and watch it come to a grinding halt until the processing has completed.
Also: Inside Linux-AI OS: I tested a distro with built-in local AI
That’s the usual case with locally-installed AI. This is especially the case when the machine in question doesn’t have an NVIDIA GPU. So, when the company requested I give its newest AMD-based mini PC geared specifically for AI a try, my first thought was that I’d see similar results as I’ve seen with other non-NVIDIA machines. I was wrong. Very wrong.
What is the AX Max Mini PC?
The VZmore AX Max Mini PC is a small form factor PC that is powered by an AMD Ryzen AI 9 HX 470, a Radeon 890M GPU, with 32 GB of SO-DIMM RAM and a 1 TB M.2 SSD. The PC measures 5.3 x 5.2 x 2.3 inches, so it doesn’t take up much space.
The device’s description says the AX Max Mini has NPU capable of processing up to 86 TOPS of overall AI performance and is designed for local AI workflows. It supports LM Studio, Ollama, and AMD GAIA for running compatible Qwen, Llama, Gemma, and DeepSeek models locally, reducing reliance on cloud-based AI services and keeping sensitive data on the device.
How did I test the AX Max Mini PC?
The first thing I did was to install Fedora Linux over the pre-installed Windows OS. I’m much more comfortable with Linux than Windows and felt I could best position myself to farely judge the hardware with the open-source OS.
Also: 7 things every Linux beginner should know before downloading their first distro
After the 2 minutes it took to install Fedora, I was ready to set the machine up for the real test. For that, I installed the Ollama GUI front end, Moose, with the command:
flatpak install flathub io.github.moooossee.MooseOnce that was installed, I let Moose download and install Ollama and then pull the qwen3-coder:30b model (because I knew I was going to use Ollama to generate a web app for testing).
Now that the machine was ready for testing, it was go time.
The test
I asked Ollama, Moose, and qwen3-coder to generate a web app that would accept user input for theatrical costume measurements, save it to a database, and allow the user to sign in and save their information.
I fully expected the machine to churn on this for a while before slowly spitting out the code. To my surprise, it immediately began the reply and eventually generated a web app that was roughly 1,500 lines of code.
I had my doubts.
Even so, I installed Apache on the machine (another reason why I installed Linux over Windows), copied the code into a file I named costume.html, moved the file into the Apache document root (/var/www/html), fired up my browser, and pointed it to http://localhost/custom.html.
Jack Wallen/ZDNETTo my surprise, the web app worked! Not only did it work, but it also worked very well. I did have to fix several issues in the code (specifically problems with the database commands), but once I had that taken care of, the app worked to perfection.
The biggest surprise for me was that, as Ollama churned through creating the various files for the app (config.php, login.php, logout.php, measurements.php, signup.php) I was able to use the machine as if nothing was happening. Even with my System76 Thelio (that includes a Ryzen 9 7900X 12-core CPU, RX 7600 Navi 33 GPU, and 32 GB of RAM), I would experience lags, stutters, and even stops when attempting to build an app with Ollama. The VZmore AX Max took on the task without so much as a blink of the digital eye.
Also: This local AI quickly replaced Ollama on my Mac – here’s why
The difference between the two machines is that the VZmore AX Max Mini CPU includes an NPU (AI Engine): XDNA 2 architecture, delivering up to 86 total AI TOPS (Tera- or Trillion-Operations Per Second, measuring how many raw AI calculations a processor can run in one second). That gives it the extra beef it needs to process AI without draining system resources for other tasks.
The conclusion is simple: The VZmore AX Max Mini is a small form factor PC that is ideal for running local AI, not only for general chat, but for far more complex processes, such as building viable applications, without bringing the system to a screeching halt.
Jack Wallen/ZDNETThis tiny machine seriously impressed me; so much so that I could see myself using this as a dedicated AI machine in my home lab. In fact, I configured Ollama such that I could connect to it from any machine on my LAN, so I didn’t have to run local AI on my primary desktop or my laptop, and it works perfectly. I will say this, however: running Ollama over a LAN isn’t nearly as fast as running it directly on the machine. However, I’ve tested this same setup using my System76 Thelio, and the speed at which the VZmore can produce output from a remote connection is considerably faster.
Final thoughts
If you want to use local AI but don’t have the space for a massive desktop PC, the VZmore AX Max Mini PC is a beast that will serve your local AI needs quite well. At $1,499, you’d be hard-pressed to find a better deal for an AI-ready PC.
Also: I tried a Claude Code rival that’s local, open source, and completely free – how it went
You also get plenty of ports to add peripherals and even connect up to four displays.
Tech specs
- Processor (CPU): AMD Ryzen AI 9 HX 470 (Zen 5 architecture; 12 cores / 24 threads: 4 Zen 5 + 8 Zen 5c)
- Graphics (GPU): AMD Radeon 890M (16 Compute Units, up to 3.1 GHz)
- AI NPU: Up to 55 NPU TOPS (86 total system AI TOPS)
- Memory (RAM): 32GB DDR5 (supports expansion up to 256GB DDR5)
- Storage: 1TB PCIe 4.0 SSD (supports dual PCIe 4.0 expansion up to 5TB)
- Cooling: V-Cooling Next-Gen Thermal Architecture (vapor chamber VC, 360° bottom intake, ~38 dB quiet operation, up to 65W sustained TDP)
- Operating System: Windows 11 Pro
- Display: Quad-display support via dual 40Gbps USB4 and dual HDMI 2.1 (up to 8K output)
- Networking: Dual 2.5G LAN ports, Wi-Fi 7
- USB Ports: 2x USB4 (40Gbps), 6x USB-A ports
- Other: SD 4.0 card reader
