Mac laptop · current · data 2026-10-15

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

Name: MacBook Pro 14"/16" (M5 Max)
Brand: Apple

With 128 GB it runs Qwen3.8 27B (needs 22.7 GB). 90 models fit. Published speed: gpt-oss-120b at 79.1 tokens/sec.

Memory36 / 48 / 64 / 128 GB

Shared between CPU and graphics.

Bandwidth614 GB/s

Higher means faster answers. 460 GB/s on the 32-core GPU (36GB only); 614 GB/s on the 40-core GPU (48/64/128GB).

PriceFrom about $4,099

As of 2026-10-15. Check before buying.

Which models fit

By memory option.

Usable: 75% on Macs and shared-memory PCs, VRAM minus 1 GB on graphics cards (estimates).
Memory	Usable	Models that fit	Best three
36 GB	27 GB	67	Qwen3.8 27B (22.7 GB), Qwen3.5 27B (21.5 GB), Qwen3.6 27B (21.5 GB)
48 GB	36 GB	76	Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB)
64 GB	48 GB	77	Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB)
128 GB	96 GB	90	Qwen3.8 27B (22.7 GB), K2 Horizon MoVA 36B-A4B (28.1 GB), Qwen3.5 27B (21.5 GB)

Speed

Published speeds.

Measured by others, with sources. Not our tests.

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

Questions

Short answers.

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.

Specs from Apple – MacBook Pro tech specs (2026-10-15). Prices are approximate and dated; 2026 prices are inflated by the memory-chip shortage.

AGENT VIEW · text/markdown · or send Accept: text/markdown

# 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.