Is the M2 Pro faster than the M2 for LLMs?

The M2 Pro reads memory about 100% faster than the M2 (200 vs 100 GB/s), so it writes about 100% faster with any model that fits both. Reading a long prompt depends on GPU compute instead, which this comparison doesn’t cover.

Which can run bigger models, the M2 or the M2 Pro?

The M2 Pro: The M2 Pro goes up to 32 GB of memory, the M2 to 24 GB. At its largest it runs 30 of 73 open models well, against 20.

M2 vs M2 Pro for local LLMs: memory, speed, which to buy

Side by side

	M2	M2 Pro
Memory sizes	8, 16, 24 GB	16, 32 GB
Memory bandwidth	100 GB/s	200 GB/s
For models, at most	about 18 GB	about 24 GB
Models that run well	20 of 73	30 of 73
MLX seat class	Core	Pro
Found in	MacBook Air (M2, 2022), MacBook Pro (13-inch, M2, 2022), MacBook Air (15-inch, M2, 2023), Mac mini (2023)	MacBook Pro (14-inch, 2023), MacBook Pro (16-inch, 2023), Mac mini (2023)

Speed with popular models

Tokens a second for one conversation, each chip at its largest memory size (24 GB and 32 GB), with the best version of the model that fits.

Model	M2	M2 Pro
Llama 3.1 8B Instruct8B	10–18 4-bit	11–19 8-bit
gpt-oss-20b21B · 3.6B active	24–42 native 4.25-bit	47–84 native 4.25-bit
Qwen3.6 35B A3B35B · 3B active	35–62 3-bit lower quality	53–94 4-bit
Qwen3.8 27B27B	3–5 4-bit	4–7 6-bit
Llama 3.3 70B Instruct70B	too big	4–7 2-bit lower quality
gpt-oss-120b117B · 5.1B active	too big	too big
Qwen3.5 122B A10B122B · 10B active	too big	too big
DeepSeek V4 Flash 0731284B · 13B active	too big	too big

Questions

Is the M2 Pro faster than the M2 for LLMs?: The M2 Pro reads memory about 100% faster than the M2 (200 vs 100 GB/s), so it writes about 100% faster with any model that fits both. Reading a long prompt depends on GPU compute instead, which this comparison doesn’t cover.
Which can run bigger models, the M2 or the M2 Pro?: The M2 Pro: The M2 Pro goes up to 32 GB of memory, the M2 to 24 GB. At its largest it runs 30 of 73 open models well, against 20.

More comparisons

The M2 for local AI · The M2 Pro for local AI · Compare every model · The best Mac for local LLMs

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.