If you look at their whitepaper (https://github.com/PrismML-Eng/Bonsai-demo/blob/main/1-bit-b...) you'll notice that it does have some tradeoffs due to model intelligence being reduced (page 10)

The average of MMLU Redux,MuSR,GSM8K,Human Eval+,IFEval,BFCLv3 for this model is 70.5 compared to 79.3 for Qwen3, that being said the model is also having a 16x smaller size and is 6x faster on a 4090....so it is a tradeoff that is pretty respectable

I'd be interested in fine tuning code here personally