Is the MacBook Air with M5 good for local LLMs?

With 32 GB it runs 28 of 73 open models well, up to Qwen3.6 35B A3B, and writes about 36–64 tokens a second with gpt-oss-20b. The M5 reads memory at 153 GB/s, which sets how fast it writes.

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

With 16 GB it runs 20 open models well; with 32 GB, 28, up to Qwen3.6 35B A3B. Memory decides which models fit, and it can’t be upgraded later.

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

By memory size

Memory	Run well	Biggest that runs well	gpt-oss-20b
16 GB153 GB/s	20	Gemma 4 12B Unified	43–77 tok/s
24 GB153 GB/s	23	Gemma 4 26B A4B	36–64 tok/s
32 GB153 GB/s	28	Qwen3.6 35B A3B	36–64 tok/s

Models: MacBook Air (13-inch, M5), MacBook Air (15-inch, M5). Not every memory size is offered with every model; Apple’s Tech Specs list what each one comes with.

Questions

Is the MacBook Air with M5 good for local LLMs?: With 32 GB it runs 28 of 73 open models well, up to Qwen3.6 35B A3B, and writes about 36–64 tokens a second with gpt-oss-20b. The M5 reads memory at 153 GB/s, which sets how fast it writes.
How much memory should a MacBook Air with M5 have for AI?: With 16 GB it runs 20 open models well; with 32 GB, 28, up to Qwen3.6 35B A3B. Memory decides which models fit, and it can’t be upgraded later.

Other Macs

The MacBook Air with other chips:

Other Macs with the M5:

MacBook Pro M5

Head to head:

The M5 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.