<!-- Markdown mirror of https://getrigbase.com/gpus/apple-m5-pro/ . Source of truth is the HTML page. Data licence: CC BY 4.0, please cite RigBase (https://getrigbase.com/gpus/apple-m5-pro/). -->
Source: https://getrigbase.com/gpus/apple-m5-pro/
Last updated: 2026-11-21

# Apple M5 Pro for local LLMs

Quick answer

**How fast is the Apple M5 Pro for local LLMs?**
The fastest plain-decode result we have is 100.24 tok/s on Qwen3.6 35B-A3B (MLX 4-bit (mlx-community/Qwen3.6-35B-A3B-4bit), mlx-lm (MLX 0.32.x)) in Mac mini M5 Pro 64GB (MLX 4-bit): Qwen3.6 35B-A3B at 100.2 tok/s, Gemma 4 26B-A4B at 85.1, Qwen3.8 27B at 17.7 (mean over 1,000 rounds). Speed depends heavily on the model, quant and engine, so compare like with like in the table. RigBase lists 10 measured results from 3 builds.

Last updated: 21 Nov 2026

10 measured results from 3 builds, each linked to its source.

| Memory | unified memory: 24–64 GB in our builds |
|---|---|
| Memory bandwidth | not listed |
| Typical EU price | not tracked yet |

## All builds with the Apple M5 Pro

| Build | GPU(s) | Memory GB (total) | Results |
|---|---|---|---|
| [Mac mini M5 Pro 64GB (MLX 4-bit): Qwen3.6 35B-A3B at 100.2 tok/s, Gemma 4 26B-A4B at 85.1, Qwen3.8 27B at 17.7 (mean over 1,000 rounds)](https://getrigbase.com/builds/mac-mini-m5-pro-64gb-mlx-1000-rewrites-pratikgx/) | Apple M5 Pro (unified, Mac mini) | 64 | 3 |
| [Mac mini M5 Pro 64GB (llama.cpp IQ4_NL): Inkling 2 Mini at 29.95 tok/s short context, 17.39 tok/s at 128k (pratikgx)](https://getrigbase.com/builds/mac-mini-m5-pro-64gb-inkling-2-mini-iq4nl-llamacpp-pratikgx/) | Apple M5 Pro (unified, Mac mini) | 64 | 5 |
| [MacBook Pro M5 Pro 24 GB: Qwen3.8 Flash-Next (125B-A6B) IQ3_XXS at 14.7 tok/s with experts streamed from SSD (MoEShift)](https://getrigbase.com/builds/macbook-pro-m5-pro-24gb-qwen38-flash-next-iq3xxs-moeshift-ssd-experts/) | Apple M5 Pro (unified) | 24 | 2 |

## All measured results
