Can a MacBook Pro M5 (14-inch), 32GB run local LLMs?
Yes — 19 of the 39 open models on this site fit in its 21 GB of usable memory, the strongest being Qwen3.8 27B. Whether that saves you money is a different question, and the answer is usually no.
Price$2,399
Memory32 GB, about 21 GB of it addressable by the GPU at 153 GB/s
Best model it runsQwen3.8 27B — Sonnet-class, 6 tok/s
Pay-back against the APIPays back in 31 years at 500k tokens a day
Run the numbers on this machine
What it runs
| Model | Speed | Class | Good at | Memory |
|---|---|---|---|---|
| Qwen3.8 27BQ4_K_M | 6.2 tok/s | Sonnet-class | 19 GB | |
| Qwen3.6 27BQ4_K_M | 6 tok/s | Haiku-class | 19 GB | |
| Muse Glimmer 30BQ4_K_M | 6.4 tok/s | Haiku-class | 18 GB | |
| Gemma 4 26B-A4BQ4_K_M | 13 tok/s | Haiku-class | 18 GB | |
| GLM-4.7-FlashQ4_K_M | 13 tok/s | Haiku-class | 20 GB | |
| Gemma 4 12BQ4_K_M | 14 tok/s | Below every hosted tier | 8.0 GB | |
| Qwen3.5 9BQ4_K_M | 17 tok/s | Below every hosted tier | 6.8 GB | |
| MiniCPM5 2BQ4_K_M | 39 tok/s | Below every hosted tier | 3.0 GB | |
| Qwen3.5 4BQ4_K_M | 30 tok/s | Below every hosted tier | 3.8 GB | |
| Ling 3.0 tinyQ4_K_M | 19 tok/s | Below every hosted tier | 6.4 GB | |
| Granite 4.2 8BQ4_K_M | 11 tok/s | Below every hosted tier | 11 GB | |
| gpt-oss-20bMXFP4 | 16 tok/s | Below every hosted tier | 13 GB |
7 more fit; the calculator lists them all.
The specifics
- Chip
- M5 (14-inch) — 10-core CPU / 10-core GPU
- Memory bandwidth
- 153 GB/s
- Usable by the GPU
- 21 GB — macOS lets the GPU wire roughly two-thirds of unified memory by default (llama.cpp discussion #2182: 66.7% at 32 GiB or less, 75% above). Raise it with `sudo sysctl iogpu.wired_limit_mb`. On a laptop, sustained speed drops once the chassis warms up and the fans cap out, so a desktop with the same chip will hold a higher tokens/sec over a long generation than the figures here suggest.
- Power under load
- 65 W (stand in) — Apple has published no power figures for the 2026 Macs, and none at all for sustained GPU load on a laptop. Stand-in: the desktop maximum for the equivalent chip (M4 Mac mini, 65 W). A laptop draws less than that, so the electricity line here is an over-estimate.
- Availability
- Shipping.
- Sources
- source 1, source 2, source 3