Running Qwen 3.6 27b Local AI on nVidia 1080ti?
Let's be honest, the nVidia 1080ti is an ancient GPU. But in the current era of Turbo Quant, turns out we can run this model on two 1080ti's with decent enough performance for a basic agentic AI setup? In this video I cover how this is possible, whether it makes sense and remember a better time when GPU's didn't cost as much as used cars. Let us know what you think in the comments below! Games footage: https://x.com/ZoldenGames OR https://t.co/u24MwZRsd7 Rent an nVidia GPU on Vast AI (15% OFF) https://cloud.vast.ai/?ref_id=74601 For sponsorships or collaboration inquiries please contact aifluxcontact@proton.me Chapters 🎬: 0:00 - intro 0:40 - why? 1:24 - gpu specs 1:54 - why quantized models break 3:00 - build overview 3:48 - model overview 5:00 - benchmarks 5:45 - what doesn't work 7:12 - next steps 7:50 - ebay pricing 8:40 - conclusion
