News for hackers. Stuff that matters.
Re:How to run Qwen 3.5 locally by ranger_danger on Monday March 09, 2026 @01:13AM (#47305122)
A 10GB 3080 still beats even an M2 Ultra with 192GB... memory bandwidth is not the only factor.

https://github.com/XiongjieDai/GPU-Benchmarks-on-LLM-Inferen...

Re:How to run Qwen 3.5 locally by seanmcdirmid on Monday March 09, 2026 @03:07AM (#47305664)
If the model is small enough to fit in to 10GB of VRAM the GPU can win.

But the bigger models are more useful, so that’s what people fixate on.