Side by side
| M1 | M1 Pro | |
|---|---|---|
| Memory sizes | 8, 16 GB | 16, 32 GB |
| Memory bandwidth | 68 GB/s | 200 GB/s |
| For models, at most | about 12 GB | about 24 GB |
| Models that run well | 14 of 73 | 30 of 73 |
| MLX seat class | Core | Pro |
| Found in | MacBook Air (M1, 2020), MacBook Pro (13-inch, M1, 2020), Mac mini (M1, 2020), iMac (24-inch, M1, 2021) | MacBook Pro (14-inch, 2021), MacBook Pro (16-inch, 2021) |
Speed with popular models
Tokens a second for one conversation, each chip at its largest memory size (16 GB and 32 GB), with the best version of the model that fits.
| Model | M1 | M1 Pro |
|---|---|---|
| Llama 3.1 8B Instruct8B | 4–6 8-bit | 11–19 8-bit |
| gpt-oss-20b21B · 3.6B active | 19–34 3-bit lower quality | 47–84 native 4.25-bit |
| Qwen3.6 35B A3B35B · 3B active | 34–60 2-bit lower quality | 53–94 4-bit |
| Qwen3.8 27B27B | 4–6 2-bit lower quality | 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 M1 Pro faster than the M1 for LLMs?
- The M1 Pro reads memory about 194% faster than the M1 (200 vs 68 GB/s), so it writes about 194% 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 or the M1 Pro?
- The M1 Pro: The M1 Pro goes up to 32 GB of memory, the M1 to 16 GB. At its largest it runs 30 of 73 open models well, against 14.
More comparisons
The M1 for local AI · The M1 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.