This is from a small model. 32B and 70B answer this correctly. "Arrowroot" too. Interestingly, 32B's "thinking" is a lot shorter and it seems to be more "sure". Could be because it's based on Qwen rather than LLaMA.
My models are both 4 bit. But yeah, that could be - small models are much worse at tolerating quantization. That's why people use LoRA to recover the accuracy somewhat even if they don't need domain adaptation.
