Re:Ask HN: Is it feasible to run a model on device for compl...
by mc7alazoun on Sunday June 07, 2026 @10:10AM
(#48435043)
Feasible but too expensive! I get that privacy is a priority for you but unfortunately if you want quality models you'd still have to maybe use frontier closed models..
[ Parent
| on HN ]
Re:Ask HN: Is it feasible to run a model on device for compl...
by mazinz on Sunday June 07, 2026 @10:12AM
(#48435065)
No open source model that’s any good?
Re:Ask HN: Is it feasible to run a model on device for compl...
by vitalyan1234 on Sunday June 07, 2026 @10:32AM
(#48435229)
the Gemma you tried is tiny, there are 31B and 26B (A4B) variants. there's also Qwen 3.6 with 27B and 35B (A3B) variants, reportedly pretty good. try them on open router or something. these require 30-40 Gb of memory to run between RAM and VRAM, less if quantized beyond near-lossless 8 bit.
there are near-SOTA open models, but they are 1T+ parameters, i.e. they require over a terabyte of memory to run.