Best Local LLMs for the MacBook Air M2 (24 GB)

The best local LLM for a MacBook Air M2 (24 GB) is Qwen3.8-27B at 5 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
100
GB/s
Models that fit
43
of 81
Top speed
47
tok/s

Considering this Mac?
Mac mini M5 Pro on Amazon → · compare every Mac for local AI →

Top 3 picks for the MacBook Air M2 (24 GB)

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

Every model ranked for a MacBook Air M2 (24 GB)

Ranked by LLMCheck suitability (capability balanced against speed on the M2). 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 2.05 tok/s est.46/50
2Qwen 3.6-27B27BApache 2.05 tok/s est.44/50
3Muse Glimmer 30B30BApache 2.04 tok/s est.42/50
4Gemma 4 31B31BApache 2.04 tok/s est.40/50
5KAT-Coder-V2.535BApache 2.09 tok/s est.39/50
6Qwen 3.6-35B-A3B35BApache 2.09 tok/s est.38/50
7Nemotron 3.5 Lightning30BOpenMDW10 tok/s est.36/50
8Gemma 4 26B-A4B26BApache 2.08 tok/s est.35/50
9GLM-4.7-Flash31BMIT4 tok/s est.35/50
10Laguna XS 2.133BOpenMDW9 tok/s est.33/50
11Bonsai 27B27BApache 2.05 tok/s33/50
12Nemotron-Cascade 230BNVIDIA Open10 tok/s est.30/50

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 MacBook Air M2

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 M2 benchmark page for exact settings.

🛒 Ready to run bigger models than the MacBook Air M2 can handle?

The MacBook Air M2 (24 GB) tops out at KAT-Coder-V2.5. Newer Apple Silicon with more unified memory runs larger, smarter models much faster:

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 MacBook Air M2

What is the best local LLM for a MacBook Air M2 (24 GB)?

Qwen3.8-27B (27.8B, Apache 2.0) is the best all-round pick at 5 tok/s on the M2. If you want maximum speed, Maple Preview 20B-A1B hits 47 tok/s; for maximum capability, Qwen 3.6-27B still fits in 24 GB.

How many models can a MacBook Air M2 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 MacBook Air M2 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