News for hackers. Stuff that matters.
Re:Cerebras Deploys Trillion-Parameter AI Models by cyanydeez on Sunday October 25, 2026 @09:54AM (#50231632)
If you have 48GB of VRAM, you should be able to get Qwen3.8-Flash-Next running and from my use, it's basically the tipping point. 27B is great for a bit of work, but I have QFN running non stop (when I can gather the correct ideas for it to implement).
Re:Cerebras Deploys Trillion-Parameter AI Models by xmddmx on Sunday October 25, 2026 @10:45AM (#50232102)
What quant and engine are you using? The smallest ones I’m seeing on ollama are > 100GB e.g. https://ollama.com/library/qwen3.8-flash-next/tags
Re:Cerebras Deploys Trillion-Parameter AI Models by sgsjchs on Sunday October 25, 2026 @01:22PM (#50233848)
This arch uses engrams aka per layer embeddings. Not all of those GBs need to go in vram.
Re:Cerebras Deploys Trillion-Parameter AI Models by cyanydeez on Monday October 26, 2026 @08:24AM (#50242479)
Halogen flash server for strix halo with quant 4. Its offloading the PLE.