It appears to be about as smart as Qwen 3.5 9b but maybe not as good as Ling 3.0 Tiny 8b-a1b

the full LFM3 collection: https://huggingface.co/collections/LiquidAI/lfm3

you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 2 weeks ago*

LFM3 1.7B and omni are surprisingly usable.

The official q8 quants are super fast but much much lower quality, so if you can go with the native bf16 weights.

I want to try fine tuning the q8 though for specific tasks, it seems like you cod get a really good balance

  • source