https://noraincheck.github.io/tags/local-llms/Recent content in Local-Llms on NoRaincheckHugoen-USNoRaincheckMon, 05 Oct 2026 00:00:00 +0000https://noraincheck.github.io/posts/localai-is-probably-good-enough/Mon, 05 Oct 2026 00:00:00 +0000https://noraincheck.github.io/posts/localai-is-probably-good-enough/<p>I think local AI on consumer devices is probably good enough now. Price is still an issue, of course, but it&rsquo;s now possible to run Qwen 3.8 Flash on 64GB of unified RAM (albeit at Q2 or Q3 quants) at a reasonable ~40+ tps with a decent context window. That alone says divorcing yourself from proprietary models is more than possible — and maybe even desirable — even if the models themselves make no further progress.</p>