Is the M2 Max faster than the M1 Max for LLMs?

About the same: their memory bandwidth is within a few percent. The M2 Max goes up to 96 GB of memory, the M1 Max to 64 GB.

Which can run bigger models, the M1 Max or the M2 Max?

The M2 Max: The M2 Max goes up to 96 GB of memory, the M1 Max to 64 GB. At its largest it runs 43 of 73 open models well, against 39.

M1 Max vs M2 Max for local LLMs: memory, speed, which to buy

Side by side

	M1 Max	M2 Max
Memory sizes	32, 64 GB	32, 64, 96 GB
Memory bandwidth	400 GB/s	400 GB/s
For models, at most	about 48 GB	about 72 GB
Models that run well	39 of 73	43 of 73
MLX seat class	Pro	Pro
Found in	MacBook Pro (14-inch, 2021), MacBook Pro (16-inch, 2021), Mac Studio (2022)	MacBook Pro (14-inch, 2023), MacBook Pro (16-inch, 2023), Mac Studio (2023)

Speed with popular models

Tokens a second for one conversation, each chip at its largest memory size (64 GB and 96 GB), with the best version of the model that fits.

Model	M1 Max	M2 Max
Llama 3.1 8B Instruct8B	21–38 8-bit	21–38 8-bit
gpt-oss-20b21B · 3.6B active	95–168 native 4.25-bit	95–168 native 4.25-bit
Qwen3.6 35B A3B35B · 3B active	56–100 8-bit	56–100 8-bit
Qwen3.8 27B27B	12–21 4-bit	12–21 4-bit
Llama 3.3 70B Instruct70B	5–8 4-bit	3–6 6-bit
gpt-oss-120b117B · 5.1B active	113–200 2-bit lower quality	67–119 native 4.25-bit
Qwen3.5 122B A10B122B · 10B active	58–103 2-bit lower quality	41–73 3-bit lower quality
DeepSeek V4 Flash 0731284B · 13B active	too big	too big

Questions

Is the M2 Max faster than the M1 Max for LLMs?: About the same: their memory bandwidth is within a few percent. The M2 Max goes up to 96 GB of memory, the M1 Max to 64 GB.
Which can run bigger models, the M1 Max or the M2 Max?: The M2 Max: The M2 Max goes up to 96 GB of memory, the M1 Max to 64 GB. At its largest it runs 43 of 73 open models well, against 39.

More comparisons

The M1 Max for local AI · The M2 Max 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.