Picking LLM for Mac Mini

The easiest way to think about local models is by memory tier. 

Mac mini Models worth considering

16GB gpt-oss-20b, smaller Gemma 4 models

24GB gpt-oss-20b, Gemma 4 26B A4B, Qwen3.6 27B

32GB Qwen3.6 35B, Qwen3-Coder 30B, Gemma 4 26B

48GB Llama 3.3 70B, alongside smaller models

64GB Llama 3.3 70B and substantially larger local workloads

These are practical starting points rather than hard limits. Quantization, context length, KV-cache requirements, runtime overhead, and whatever else is running on the Mac all affect how comfortably a model runs. 

A model that technically fits into memory may still be unpleasant to use if there is not enough headroom.