Is the MacBook Pro with M5 Max good for local LLMs?

With 128 GB it runs 47 of 73 open models well, up to Qwen3.5 122B A10B, and writes about 145–259 tokens a second with gpt-oss-20b. The M5 Max reads memory at 614 GB/s, which sets how fast it writes.

How much memory should a MacBook Pro with M5 Max have for AI?

With 36 GB it runs 38 open models well; with 128 GB, 47, up to Qwen3.5 122B A10B. Memory decides which models fit, and it can’t be upgraded later.

MacBook Pro M5 Max for local AI: which LLMs it runs, by memory

By memory size

Memory	Run well	Biggest that runs well	gpt-oss-20b
36 GB460 GB/s	38	Qwen3.6 35B A3B	109–194 tok/s
48 GB614 GB/s	38	Qwen3.6 35B A3B	145–259 tok/s
64 GB614 GB/s	39	Nemotron 3.5 Bolt 74B A9B	145–259 tok/s
128 GB614 GB/s	47	Qwen3.5 122B A10B	145–259 tok/s

Models: MacBook Pro (14-inch, M5 Pro or M5 Max), MacBook Pro (16-inch, M5 Pro or M5 Max). Not every memory size is offered with every model; Apple’s Tech Specs list what each one comes with.

Questions

Is the MacBook Pro with M5 Max good for local LLMs?: With 128 GB it runs 47 of 73 open models well, up to Qwen3.5 122B A10B, and writes about 145–259 tokens a second with gpt-oss-20b. The M5 Max reads memory at 614 GB/s, which sets how fast it writes.
How much memory should a MacBook Pro with M5 Max have for AI?: With 36 GB it runs 38 open models well; with 128 GB, 47, up to Qwen3.5 122B A10B. Memory decides which models fit, and it can’t be upgraded later.

Other Macs

The MacBook Pro with other chips:

Other Macs with the M5 Max:

Mac Studio M5 Max

Head to head:

Against PCs and graphics cards:

The M5 Max 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.