← Back to context

Comment by Tokumei-no-hito

3 days ago

thanks for sharing. are some local models better than others? can small models work well or do you want 8B+?

3 comments

Tokumei-no-hito

Reply
vunderba  3 days ago

So in my experience smaller models tend to produce worse results BUT I actually got really good transcription cleanup with CoT (Chain of Thought models) like Qwen even quantized down to 8b.

  • dragonwriter  3 days ago

    I think the 8B+ question was about parameter count (8 billion+ parameters), not quantization level (8 bits per weight).

    • vunderba  3 days ago

      Yeah I should have been more specific - Qwen 8b at a 5_K_M quant worked very well.