Comment on I'm looking for an article showing that LLMs don't know how they work internally

<- View Parent
theunknownmuncher@lemmy.world ⁨1⁩ ⁨week⁩ ago

I’ve been very unimpressed by gemma3. 1b, 4b, 12b? 27b is probably your best chance at coherent results. Try qwen3:32b

source
Sort:hotnewtop