BlameThePeacock@lemmy.catoSelfhosted@lemmy.world•Hardware for local inference?English
14·
2 months agoI’m running Qwen 3.6 35B A3B (the MoE model) on an 8GB Vram Nvidia GPU with 32 GB of ram, with tweaking (and Turboquant) I’ve got it up to 30-40 Tokens per second and a 260k Context. It’s very usable. I’ve seen people report success with Dual 3060 Cards, but you’re still talking $1000-1500 for that kind of setup even if you have parts of it already.
You can always try out the OG Tier 1 Crafting System, Star Wars Galaxies. There are a handful of independent servers still running and actively adding content.
SWG Restoration has a few hundred people online most of the time. https://swgr.org/home/