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

• theunknownmuncher@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

  ollama is not an LLM, but a program used to run them. What model are you running?

  source

  • A_Union_of_Kobolds@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

    Yes I’m well aware thank you.

    Gemma3 was latest when I installed it.

    source

    • theunknownmuncher@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

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

      source