FYI after quite a bit of testing I settled on qwen2.5 coder 1.5b for autocomplete and llama 3.2 1b for chat. These models are tiny, but bigger models had too poor of speed performance on an M1 laptop for daily use. Iβm sure the results will pale in comparison to larger models, but it is certainly better than nothing for free!
FYI after quite a bit of testing I settled on qwen2.5 coder 1.5b for autocomplete and llama 3.2 1b for chat. These models are tiny, but bigger models had too poor of speed performance on an M1 laptop for daily use. Iβm sure the results will pale in comparison to larger models, but it is certainly better than nothing for free!
FYI after quite a bit of testing I settled on qwen2.5 coder 1.5b for autocomplete and llama 3.2 1b for chat. These models are tiny, but bigger models had too poor of speed performance on an M1 laptop for daily use. Iβm sure the results will pale in comparison to larger models, but it is certainly better than nothing for free!
In the time span of other countries, the US is a dumb teenager with way to
much money. We spend it all on "cool" shit like weapons, and think education
is stupid
-colehoots, Nov 2015
In the time span of other countries, the US is a dumb teenager with way to
much money. We spend it all on "cool" shit like weapons, and think education
is stupid
-colehoots, Nov 2015