Is the Mac mini with M1 good for local LLMs?

With 16 GB it runs 14 of 73 open models well, up to Gemma 4 E4B, and writes about 19–34 tokens a second with gpt-oss-20b. The M1 reads memory at 68 GB/s, which sets how fast it writes.

How much memory should a Mac mini with M1 have for AI?

With 8 GB it runs 14 open models well; with 16 GB, 14, up to Gemma 4 E4B. Memory decides which models fit, and it can’t be upgraded later.

Mac mini M1 for local AI: which LLMs it runs, by memory

By memory size

Memory	Run well	Biggest that runs well	gpt-oss-20b
8 GB68 GB/s	14	Gemma 4 E4B	too big
16 GB68 GB/s	14	Gemma 4 E4B	19–34 tok/s

Models: Mac mini (M1, 2020). Not every memory size is offered with every model; Apple’s Tech Specs list what each one comes with.

Questions

Is the Mac mini with M1 good for local LLMs?: With 16 GB it runs 14 of 73 open models well, up to Gemma 4 E4B, and writes about 19–34 tokens a second with gpt-oss-20b. The M1 reads memory at 68 GB/s, which sets how fast it writes.
How much memory should a Mac mini with M1 have for AI?: With 8 GB it runs 14 open models well; with 16 GB, 14, up to Gemma 4 E4B. Memory decides which models fit, and it can’t be upgraded later.

Other Macs

The Mac mini with other chips:

Other Macs with the M1:

Head to head:

The M1 for local AI · The best Mac for local LLMs · Every Mac

How it’s worked out

Memory: the model’s parameters at 8, 6, 4, 3 or 2 bits per weight plus MLX’s group scales (half a bit per weight), or its native format, with room for the context on top. By default macOS lets the GPU use about 75% of unified memory. Speed: memory bandwidth divided by the bytes read per token is the ceiling for one conversation; in llama.cpp’s public Apple Silicon benchmarks real runs reach about 45% to 80% of it, which is the range shown. These are estimates, not measurements: measure your own Mac on MLX Bench. Model figures from each official model card, chip figures from Apple’s Tech Specs. Checked 2026-10-19. Same data as mlx.app/compare.