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

The M2 Ultra reads memory about 100% faster than the M2 Max (800 vs 400 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 Max or the M2 Ultra?

The M2 Ultra: The M2 Ultra goes up to 192 GB of memory, the M2 Max to 96 GB. At its largest it runs 49 of 73 open models well, against 43.

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

Side by side

	M2 Max	M2 Ultra
Memory sizes	32, 64, 96 GB	64, 128, 192 GB
Memory bandwidth	400 GB/s	800 GB/s
For models, at most	about 72 GB	about 144 GB
Models that run well	43 of 73	49 of 73
MLX seat class	Pro	Ultra
Found in	MacBook Pro (14-inch, 2023), MacBook Pro (16-inch, 2023), Mac Studio (2023)	Mac Studio (2023), Mac Pro (2023), Mac Pro (Rack, 2023)

Speed with popular models

Tokens a second for one conversation, each chip at its largest memory size (96 GB and 192 GB), with the best version of the model that fits.

Model	M2 Max	M2 Ultra
Llama 3.1 8B Instruct8B	21–38 8-bit	42–75 8-bit
gpt-oss-20b21B · 3.6B active	95–168 native 4.25-bit	189–337 native 4.25-bit
Qwen3.6 35B A3B35B · 3B active	56–100 8-bit	113–200 8-bit
Qwen3.8 27B27B	12–21 4-bit	13–22 8-bit
Llama 3.3 70B Instruct70B	3–6 6-bit	5–9 8-bit
gpt-oss-120b117B · 5.1B active	67–119 native 4.25-bit	133–237 native 4.25-bit
Qwen3.5 122B A10B122B · 10B active	41–73 3-bit lower quality	34–60 8-bit
DeepSeek V4 Flash 0731284B · 13B active	too big	63–112 3-bit lower quality

Questions

Is the M2 Ultra faster than the M2 Max for LLMs?: The M2 Ultra reads memory about 100% faster than the M2 Max (800 vs 400 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 Max or the M2 Ultra?: The M2 Ultra: The M2 Ultra goes up to 192 GB of memory, the M2 Max to 96 GB. At its largest it runs 49 of 73 open models well, against 43.

More comparisons

The M2 Max for local AI · The M2 Ultra 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.