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

The M1 Ultra reads memory about 100% faster than the M1 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 M1 Max or the M1 Ultra?

The M1 Ultra: The M1 Ultra goes up to 128 GB of memory, the M1 Max to 64 GB. At its largest it runs 47 of 73 open models well, against 39.

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

Side by side

	M1 Max	M1 Ultra
Memory sizes	32, 64 GB	64, 128 GB
Memory bandwidth	400 GB/s	800 GB/s
For models, at most	about 48 GB	about 96 GB
Models that run well	39 of 73	47 of 73
MLX seat class	Pro	Ultra
Found in	MacBook Pro (14-inch, 2021), MacBook Pro (16-inch, 2021), Mac Studio (2022)	Mac Studio (2022)

Speed with popular models

Tokens a second for one conversation, each chip at its largest memory size (64 GB and 128 GB), with the best version of the model that fits.

Model	M1 Max	M1 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	5–8 4-bit	5–9 8-bit
gpt-oss-120b117B · 5.1B active	113–200 2-bit lower quality	133–237 native 4.25-bit
Qwen3.5 122B A10B122B · 10B active	58–103 2-bit lower quality	64–114 4-bit
DeepSeek V4 Flash 0731284B · 13B active	too big	88–156 2-bit lower quality

Questions

Is the M1 Ultra faster than the M1 Max for LLMs?: The M1 Ultra reads memory about 100% faster than the M1 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 M1 Max or the M1 Ultra?: The M1 Ultra: The M1 Ultra goes up to 128 GB of memory, the M1 Max to 64 GB. At its largest it runs 47 of 73 open models well, against 39.

More comparisons

The M1 Max for local AI · The M1 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.