Is the M3 Ultra faster than the M3 Max for LLMs?

The M3 Ultra reads memory about 105% faster than the M3 Max (819 vs 400 GB/s), so it writes about 105% 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 M3 Max or the M3 Ultra?

The M3 Ultra: The M3 Ultra goes up to 512 GB of memory, the M3 Max to 128 GB. At its largest it runs 60 of 73 open models well, against 47.

M3 Max vs M3 Ultra for local LLMs: memory, speed, which to buy

Side by side

	M3 Max	M3 Ultra
Memory sizes	36, 48, 64, 96, 128 GB	96, 256, 512 GB
Memory bandwidth	300–400 GB/s	819 GB/s
For models, at most	about 96 GB	about 384 GB
Models that run well	47 of 73	60 of 73
MLX seat class	Pro	Ultra
Found in	MacBook Pro (14-inch, M3 Pro or M3 Max, Nov 2023), MacBook Pro (16-inch, Nov 2023)	Mac Studio (2025)

Speed with popular models

Tokens a second for one conversation, each chip at its largest memory size (128 GB and 512 GB), with the best version of the model that fits.

Model	M3 Max	M3 Ultra
Llama 3.1 8B Instruct8B	21–38 8-bit	43–77 8-bit
gpt-oss-20b21B · 3.6B active	95–168 native 4.25-bit	194–345 native 4.25-bit
Qwen3.6 35B A3B35B · 3B active	56–100 8-bit	115–205 8-bit
Qwen3.8 27B27B	12–21 4-bit	13–23 8-bit
Llama 3.3 70B Instruct70B	2–4 8-bit	5–9 8-bit
gpt-oss-120b117B · 5.1B active	67–119 native 4.25-bit	137–243 native 4.25-bit
Qwen3.5 122B A10B122B · 10B active	32–57 4-bit	35–62 8-bit
DeepSeek V4 Flash 0731284B · 13B active	44–78 2-bit lower quality	27–47 8-bit

Questions

Is the M3 Ultra faster than the M3 Max for LLMs?: The M3 Ultra reads memory about 105% faster than the M3 Max (819 vs 400 GB/s), so it writes about 105% 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 M3 Max or the M3 Ultra?: The M3 Ultra: The M3 Ultra goes up to 512 GB of memory, the M3 Max to 128 GB. At its largest it runs 60 of 73 open models well, against 47.

More comparisons

The M3 Max for local AI · The M3 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.