The best local LLM for a Mac mini M6 (32 GB) is Qwen3.8-27B at 8 tok/s. With 32 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.
Ranked by LLMCheck suitability (capability balanced against speed on the M6). 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 →
| # | Model | Size | License | Speed | Capability |
|---|---|---|---|---|---|
| 1 | Qwen3.8-27B | 27.8B | Apache 2.0 | 8 tok/s | 46/50 |
| 2 | Qwen 3.6-27B | 27B | Apache 2.0 | 9 tok/s | 44/50 |
| 3 | Muse Glimmer 30B | 30B | Apache 2.0 | 8 tok/s | 42/50 |
| 4 | Gemma 4 31B | 31B | Apache 2.0 | 7 tok/s est. | 40/50 |
| 5 | KAT-Coder-V2.5 | 35B | Apache 2.0 | 15 tok/s | 39/50 |
| 6 | Qwen 3.6-35B-A3B | 35B | Apache 2.0 | 14 tok/s | 38/50 |
| 7 | Nemotron 3.5 Lightning | 30B | OpenMDW | 17 tok/s | 36/50 |
| 8 | Gemma 4 26B-A4B | 26B | Apache 2.0 | 14 tok/s | 35/50 |
| 9 | GLM-4.7-Flash | 31B | MIT | 7 tok/s est. | 35/50 |
| 10 | Laguna XS 2.1 | 33B | OpenMDW | 16 tok/s est. | 33/50 |
| 11 | Bonsai 27B | 27B | Apache 2.0 | 8 tok/s est. | 33/50 |
| 12 | Nemotron-Cascade 2 | 30B | NVIDIA Open | 16 tok/s est. | 30/50 |
Showing the top 12 of 43 models that fit in 32 GB. See the full leaderboard or all benchmarks.
The fastest way to get started is Ollama. Install it, then pull the top pick for your Mac:
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 M6 benchmark page for exact settings.
The Mac mini M6 (32 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.
Qwen3.8-27B (27.8B, Apache 2.0) is the best all-round pick at 8 tok/s on the M6. If you want maximum speed, LFM2.5-2.6B hits 81 tok/s; for maximum capability, Qwen 3.6-27B still fits in 32 GB.
About 43 of the 81 models in the LLMCheck leaderboard fit in 32 GB of unified memory, from compact models up to KAT-Coder-V2.5 (35B).
Not comfortably. A 70B model in Q4 needs ~40–44 GB; with 32 GB you should stick to models up to ~26 GB, such as Qwen3.8-27B. For 70B, look at a 48 GB+ Mac.
32 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.