# MacBook Pro 14"/16" (M5 Max) for local AI

URL: https://insidethemachine.ai/machines/macbook-pro-m5-max
Type: Mac laptop. Chip: M5 Max (32- or 40-core GPU). Memory: unified, options 36, 48, 64, 128 GB. Bandwidth: 614 GB/s (460 GB/s on the 32-core GPU (36GB only); 614 GB/s on the 40-core GPU (48/64/128GB).). Spec source: https://www.apple.com/macbook-pro/specs/ (2026-10-15).
Price: from about $4,099 (2026-10-15, approximate). Status: current.

## Which models fit

| memory GB | usable GB | models that fit | best 3 |
|---|---|---|---|
| 36 | 27 | 67 | Qwen3.8 27B (22.7 GB), Qwen3.5 27B (21.5 GB), Qwen3.6 27B (21.5 GB) |
| 48 | 36 | 76 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) |
| 64 | 48 | 77 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) |
| 128 | 96 | 90 | Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB) |

## Published speeds (not our tests)

- gpt-oss-120b: 79.1 tok/s decode (Ollama 0.34.1, MXFP4 (GGUF), 16" MBP M5 Max 40c, 128GB (Joel Ramat via bestllmfor.com, 2026-09-16), community-measured) https://llamaperf.com/model/gpt-oss (2026-10-15)
- gpt-oss-20b: 113.4 tok/s decode (Ollama 0.34.1, MXFP4 (GGUF), 16" MBP M5 Max 40c, 128GB, community-measured) https://llamaperf.com/model/gpt-oss (2026-10-15)
- Qwen3.8 27B: 36.6 tok/s decode (Ollama 0.34.1, GGUF Q4 (17 GB), 16" MBP M5 Max 40c, 128GB, community-measured) https://llamaperf.com/model/gpt-oss (2026-10-15)
- Qwen3.8 27B: 68 tok/s decode (Ollama 0.34.1 (MLX), MLX (18 GB), 16" MBP M5 Max 40c, 128GB, community-measured) https://llamaperf.com/model/gpt-oss (2026-10-15)
- Qwen3.6 35B-A3B: 167.2 tok/s decode (Ollama 0.34.1 (MLX), MLX (23 GB), 16" MBP M5 Max 40c, 128GB, community-measured) https://llamaperf.com/model/gpt-oss (2026-10-15)
- Gemma 4 12B: 58.1 tok/s decode (Ollama 0.34.1, GGUF Q4 (7.6 GB), 16" MBP M5 Max 40c, 128GB, community-measured) https://llamaperf.com/model/gpt-oss (2026-10-15)

## Questions

**What is the best local LLM for the MacBook Pro 14"/16" (M5 Max)?**
With 128 GB, Qwen3.8 27B (needs 22.7 GB, AA 33.7). 90 of 124 models fit. With 36 GB: Qwen3.8 27B.

**How fast is the MacBook Pro 14"/16" (M5 Max) for local AI?**
Published: gpt-oss-120b at 79.1 tokens/sec (Ollama 0.34.1, 16" MBP M5 Max 40c, 128GB (Joel Ramat via bestllmfor.com, 2026-09-16)); gpt-oss-20b at 113.4 tokens/sec (Ollama 0.34.1, 16" MBP M5 Max 40c, 128GB). These are other people's measurements, not ours.

**How much does the MacBook Pro 14"/16" (M5 Max) cost?**
From about $4,099 (as of 2026-10-15). 2026 prices are inflated by the memory-chip shortage; check before buying.