Asus GX10 - Run 408 billion parameter AI model locally (AI super computer) #nvidiagpus #ai #nvidia
This title could be clearer and more informative.Try out Clickbait Shieldfor free (5 uses left this month).
A hands-on unboxing and demo of the ASUS Ascent GX10, a compact AI inference server capable of running large language models with up to 408 billion parameters locally. The video demonstrates running 20B and 120B parameter models via Ollama on the machine's 128GB LPDDR memory, highlighting fast local inference speeds and privacy benefits compared to cloud-based AI services like ChatGPT.
•1m watch time
15 Impressions