See more imageswould recommend to a friend
cdunbar Posted
I bought one of these to run local LLMs for my OpenClaw adventures. I was having so much fun that I bought a second one and set up a cluster. That process was very straightforward, and the hardware has been great. The cluster has been up 20+ days so far without a hiccup. I can’t promise I won’t buy another one (or two) of these.
This review is from ASUS - Ascent GX10 Mini Desktop - NVIDIA GB10 (2025) - 128GB Memory - 1TB Storage - Black
Bryan Posted
Fantastic! Does exactly what I need. I found it works best if you do not try to work directly on the device but have it host an AI api. then you can have a workstation with all your tools reach out to it without bogging down the system with a load of software that interferes with its AI performance. I look forward to getting a couple more and building a cluster. So far I have not encountered anything negative on this device. it has simply done everything I asked it to.
RANDYP Posted
I purchased this piece of junk and I was really really excited to use it for local LLMs but literally on day 2 trying to run the Qwen 3.6 model via the build.nvidia.com/spark guides it has done nothing but CRASH!! I'm using the Nvidia build guide-recommended Hermes Agent setup also and it has crashed several times yesterday. So thoroughly disgusted with Asus and Nvidia and the bugs and issues thus unit has!!!I've updated it, has the latest BIOS, I'm SO MAD I'M going to ask for my money back! WHAT AN ABSOLUTE piece of hot garbage!! I've been building my own PCs for years but I'm not a coder, but this was supposed to be a turn-key solution for users who wanted to run large local LLMs! I'm SO MAD!!
Posted
Dear RANDYP,
Thank you for your comment.
We do understand your disappointment with the GX10 Mini Desktop and the inconvenience this may have caused if you are experiencing system crash while running Qwen 3.6. The crashes is due to NVIDIA GB10 power-delivery throttling or high-context memory spikes. To resolve this problem, reset the power brick, optimize quantization flags, and manage swap settings to restore stability. Additonally, adjust your memory settings to avoid kernel panics, run efficient quantized versions (like 4-bit or 8-bit Qwen 3.6 builds) instead of raw weights to reduce memory load and update the engine flags. For helpful tips, visit the Nvidia Developer Forums for hardware stability tips. Furthermore, ensure Nvidia DGX OS is up to date. The most current OS version is posted at: https://www.asus.com/networking-iot-servers/desktop-ai-supercomputer/ultra-small-ai-supercomputers/asus-ascent-gx10/helpdesk_download?model2Name=ASUS-Ascent-GX10 .
Should you need further assistance with the product, please email me at cl-rodel@asus.com and I would be more than happy to help. Or, you are most welcome to call Product Support Hotline at: 1(888) 678-3688. Also, you can chat with an ASUS live support agent from the link: https://www.asus.com/us/support/article/1135/.
Thank you for choosing an ASUS product.
Regards,
Rodel
ASUS Customer Loyalty