How to Run a Local LLM on a Mac in 2026

A Mac with 32GB of unified memory will run a 20 billion parameter model at 4-bit without complaint. A 16GB Mac will not. That one number decides almost everything else about running a local LLM on a Mac, so start there rather than with the model you want.

Work out your memory ceiling first

On Apple silicon the GPU is rarely the limit. Unified memory is. The rough working rule: take the model size in billions of parameters, multiply by 0.6, and that is roughly the gigabytes of memory the weights need at 4-bit quantisation. A 14B model wants about 8.4GB before anything else loads.

Then leave headroom. Context windows are stored on top of the weights, and a long one is not free. If you have already read our VRAM requirements breakdown, the same arithmetic applies here with unified memory in place of dedicated VRAM.

Pick a runner

Three options cover almost everyone. Ollama is the fastest way in: one command pulls a model and starts talking to it. LM Studio gives you a GUI, a model browser and a local API server. llama.cpp is what the other two are built on, and it is the right choice if you want every knob exposed.

Choose a quantisation

Q4_K_M is the default answer. Moving up to 8-bit roughly doubles the memory for a quality difference most people cannot reliably pick out in ordinary use. Dropping to 3-bit saves memory and starts to show, particularly on longer reasoning chains.

Match the model to the job

Small models in the 3B to 8B range are genuinely good at autocomplete, summarising, reformatting and tidying text, and they run fast enough to feel instant. Mid-size models around 14B to 32B handle reasoning tasks passably. The frontier stays in the cloud, and pretending otherwise wastes an afternoon.

Know when local loses

A local model has no idea what happened this morning, cannot search, and will not hold a million-token context. For current information, very long documents or best-in-class reasoning, a hosted model still wins. Local wins on privacy, on latency, and on the fact that there is no monthly bill.

What to buy if you are starting from scratch

The new Mac mini M6 ships on 22 September and is being pitched squarely at this use case. If you would rather not wait, the outgoing M4 model is available now in a 24GB configuration, which is a comfortable place to sit. On the Windows side the RTX Spark route solves the same problem differently and costs more.

Whichever you choose, buy the memory rather than the cores. Cores make a model faster. Memory decides whether it runs at all.

Some links in this article are affiliate links. We may earn a small commission at no extra cost to you.