Post #3955081
2026-07-13 19:51 UTC
@Lydie@tech.lgbt I've been using an i7 4790k, 32GB DDR3 and dual 5060 Ti's for local models, gemma4, qwen3.6 etc. not solar powered unfortunately
Replies (2)
-
@ben@social.benjaminturner.me 2026-07-13 19:56
@Lydie@tech.lgbt I suppose it is technically hydro-powered since I'm in Seattle, so some solace there 😅
-
@Lydie@tech.lgbt 2026-07-13 20:04
@ben@social.benjaminturner.me Nice. Amazing how well these old platforms work for this. Just using them to glue a bunch of GPUs together. What size models does that run and how many tokens per second? I'm getting around 64t/s on my old 2080tis