Log inCreate wallet

MacBook Pro with M3 Max for local AI.

The M3 Max reads memory at 400 GB/s, which sets how fast it writes. Memory decides which models fit, and it can’t be upgraded later, so pick the size here.

64 GB39 models run wellNemotron 3.5 Bolt 74B A9B · 35–63 tok/s96 GB38 models run wellgpt-oss-120b · 50–89 tok/s128 GB47 models run wellQwen3.5 122B A10B · 32–57 tok/s

By memory size

MemoryRun wellBiggest that runs wellgpt-oss-20b
36 GB300 GB/s33Qwen3.6 35B A3B71–126 tok/s
48 GB400 GB/s38Qwen3.6 35B A3B95–168 tok/s
64 GB400 GB/s39Nemotron 3.5 Bolt 74B A9B95–168 tok/s
96 GB300 GB/s38gpt-oss-120b71–126 tok/s
128 GB400 GB/s47Qwen3.5 122B A10B95–168 tok/s

Models: MacBook Pro (14-inch, M3 Pro or M3 Max, Nov 2023), MacBook Pro (16-inch, Nov 2023). 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 M3 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 95–168 tokens a second with gpt-oss-20b. The M3 Max reads memory at 400 GB/s, which sets how fast it writes.
How much memory should a MacBook Pro with M3 Max have for AI?
With 36 GB it runs 33 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:

Head to head:

The M3 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.

MacBook Pro M3 Max for local AI: which LLMs it runs, by memory