Best Local LLMs for the MacBook Air M3 (24 GB)

The best local LLM for a MacBook Air M3 (24 GB) is Qwen3.8-27B at 5 tok/s (estimated). With 24 GB of unified memory it runs 43 of the models in the LLMCheck index — 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 89
Top speed
estimated175
tok/s

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

Top 3 picks for the MacBook Air M3 (24 GB)

⭐ Best overall
27.8B · Apache 2.0 · cap 46/50
estimated5 tok/s
⚡ Fastest
20B · MIT · cap 20/50
estimated175 tok/s
🧠 Runner-up
27B · Apache 2.0 · cap 44/50
estimated5 tok/s

Every model ranked for a MacBook Air M3 (24 GB)

Ranked by LLMCheck suitability (capability balanced against speed on the M3). Click a model for its full benchmark and setup. Every speed carries its provenance mark: most are index estimates from the memory-bandwidth model, and a filled square is a published measurement — submit a real run →

#ModelSizeLicenseSpeedCapability
1Qwen3.8-27B27.8BApache 2.0estimated5 tok/s46/50
2Qwen 3.6-27B27BApache 2.0estimated5 tok/s44/50
3Muse Glimmer 30B30BApache 2.0estimated5 tok/s42/50
4Gemma 4 31B31BApache 2.0estimated4 tok/s40/50
5KAT-Coder-V2.535BApache 2.0estimated9 tok/s39/50
6Qwen 3.6-35B-A3B35BApache 2.0estimated8 tok/s38/50
7Nemotron 3.5 Lightning30BOpenMDWestimated10 tok/s36/50
8Gemma 4 26B-A4B26BApache 2.0estimated8 tok/s35/50
9GLM-4.7-Flash31BMITestimated4 tok/s35/50
10Maple Preview 20B-A1B20BMITestimated175 tok/s20/50
11Laguna XS 2.133BOpenMDWestimated9 tok/s33/50
12Bonsai 27B27BApache 2.0estimated5 tok/s33/50
Provenance key
sourced
Published figure — vendor or press review
estimated
community
Linked individual run — blog, forum or submission

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 M3

The fastest way to get started is Ollama. Install it, then find the top pick for your Mac in its library and copy the exact tag it lists:

brew install ollama

Find Qwen3.8-27B in the Ollama library → · model card on Hugging Face →

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 M3 benchmark page for exact settings.

🛒 Ready to run bigger models than the MacBook Air M3 can handle?

The MacBook Air M3 (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 M3

What is the best local LLM for a MacBook Air M3 (24 GB)?

Qwen3.8-27B (27.8B, Apache 2.0) is the best all-round pick at 5 tok/s (estimated) on the M3. If you want maximum speed, Maple Preview 20B-A1B hits 175 tok/s (estimated); for maximum capability, Qwen 3.6-27B still fits in 24 GB.

How many models can a MacBook Air M3 with 24 GB run?

About 43 of the 89 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 M3 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