alt Hacker News12GB GPU is useless. The good experience is with 128-256GB unified memory architectures like strix halo etc. You don't need to buy any hardware, you can experience the latest open weight MOE (flash) models from DeepSeek, qwen, or GLM on openrouter using a local agent like kilo.
Replies
the__alchemist • yesterday at 8:06 PM
That is a shift of comparisons though, right? This thread was about running locally, explicitly as an alternative to cloud services. I would guess few people have graphics cards with > 12GB ram.
➕ show 2 replies
dofm • yesterday at 8:06 PM
Would you talk to me a mo about Kilo compared to Pi?
I am digging in on Pi (in lovely Paseo and exploring Pendant when in VS Code).
What would I find better or worse in Kilo?
A 3060 + good chunk of system RAM can run qwen3.8 flash next.