You're not running a deepseek model on your macbook.

Gemma is Google's distillation of their larger Gemini model (at least that's my understanding.) Qwen is alibab's model. Qwen is usually very good at code, gemma tends to be a little better at everything else.

There are Deepseek distills that use either qwen or gemma as a base. I haven't been impressed with them though. TBH I've felt like most of the reasoning models are overhyped.