Best Local LLMs for the Mac mini M5 Pro (24 GB)

The best local LLM for a Mac mini M5 Pro (24 GB) is Qwen3.8-27B at 15 tok/s. With 24 GB of unified memory it runs 43 of the models we benchmark — from compact options up to 35B-class models. For everyday chat and coding, Qwen3.8-27B is the sweet spot. Full ranking below.

Unified memory
24
GB
Mem. bandwidth
307
GB/s
Models that fit
43
of 81
Top speed
281
tok/s

Top 3 picks for the Mac mini M5 Pro (24 GB)

⭐ Best overall
27.8B · Apache 2.0 · cap 46/50
15 tok/s
⚡ Fastest
20B · MIT · cap 20/50
281 tok/s
🧠 Runner-up
27B · Apache 2.0 · cap 44/50
14 tok/s

Every model ranked for a Mac mini M5 Pro (24 GB)

Ranked by LLMCheck suitability (capability balanced against speed on the M5 Pro). Click a model for its full benchmark and setup. All speeds are index estimates (memory-bandwidth model, cross-referenced with sourced benchmarks where available) — submit a real run →

#ModelSizeLicenseSpeedCapability
1Qwen3.8-27B27.8BApache 2.015 tok/s est.46/50
2Qwen 3.6-27B27BApache 2.014 tok/s44/50
3Muse Glimmer 30B30BApache 2.014 tok/s est.42/50
4KAT-Coder-V2.535BApache 2.027 tok/s est.39/50
5Gemma 4 31B31BApache 2.013 tok/s est.40/50
6Qwen 3.6-35B-A3B35BApache 2.027 tok/s est.38/50
7Nemotron 3.5 Lightning30BOpenMDW31 tok/s est.36/50
8Gemma 4 26B-A4B26BApache 2.035 tok/s35/50
9GLM-4.7-Flash31BMIT13 tok/s est.35/50
10Laguna XS 2.133BOpenMDW28 tok/s est.33/50
11Maple Preview 20B-A1B20BMIT281 tok/s20/50
12Bonsai 27B27BApache 2.015 tok/s est.33/50

Showing the top 12 of 43 models that fit in 24 GB. See the full leaderboard or all benchmarks.

Quick start: run Qwen3.8-27B on your Mac mini M5 Pro

The fastest way to get started is Ollama. Install it, then pull the top pick for your Mac:

brew install ollama
ollama run qwen38-27b

Prefer a GUI? LM Studio gives you a one-click download and chat window. For step-by-step help see our Ollama install guide, or open the Qwen3.8-27B on M5 Pro benchmark page for exact settings.

🛒 Get a Mac mini M5 Pro for local AI

The Mac mini M5 Pro (24 GB) comfortably runs 43 of the models we benchmark, led by Qwen3.8-27B. Grab one and start running LLMs offline today:

As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence our rankings.

FAQ: local LLMs on the Mac mini M5 Pro

What is the best local LLM for a Mac mini M5 Pro (24 GB)?

Qwen3.8-27B (27.8B, Apache 2.0) is the best all-round pick at 15 tok/s on the M5 Pro. If you want maximum speed, Maple Preview 20B-A1B hits 281 tok/s; for maximum capability, Qwen 3.6-27B still fits in 24 GB.

How many models can a Mac mini M5 Pro with 24 GB run?

About 43 of the 81 models in the LLMCheck leaderboard fit in 24 GB of unified memory, from compact models up to KAT-Coder-V2.5 (35B).

Can a Mac mini M5 Pro run a 70B model?

Not comfortably. A 70B model in Q4 needs ~40–44 GB; with 24 GB you should stick to models up to ~18 GB, such as Qwen3.8-27B. For 70B, look at a 48 GB+ Mac.

Is 24 GB of RAM enough to run LLMs locally?

24 GB is great for small-to-mid models (up to ~14B comfortably); for 30B+ you'll want 32 GB or more. Because Apple Silicon uses unified memory, that figure is both your system RAM and your VRAM.

Related