The best local LLM for a Mac mini M2 Pro (32 GB) is Qwen 3.6-35B-A3B at ~71 tok/s (estimated), the top-ranked model that reaches 15 tok/s here. Its 32 GB fits 58 of the 116 models in the LLMCheck index, up to 39.8B-class. The most capable, Qwen3.8-27B, runs at ~11 tok/s (estimated): slow for chat.
Considering this Mac?
Mac mini M5 Pro on Amazon → · compare every Mac for local AI →
Ranked by LLMCheck suitability (capability balanced against speed on the M2 Pro); the top pick is the best-ranked model that reaches 15 tok/s here and has a standard Mac runtime, and slower models are tagged slow. Click a model for its full figures and setup. Every speed carries its provenance mark: most are index estimates from the memory-bandwidth model, a filled square is a published figure and a hollow circle a community run — submit a real run →
| # | Model | Size | License | Speed | Capability |
|---|---|---|---|---|---|
| 1 | Qwen 3.6-35B-A3B | 35B MoE | Apache 2.0 | estimated71 tok/s | 38/50 |
| 2 | Qwen3.8-27B slow | 27.8B | Apache 2.0 | estimated11 tok/s | 46/50 |
| 3 | LFM2.5-24B-A2B | 24B MoE | LFM Open | estimated87 tok/s | 35/50 |
| 4 | KAT-Coder-V2.5 | 35B MoE | Apache 2.0 | estimated53 tok/s | 39/50 |
| 5 | Qwen 3.6-27B slow | 27B | Apache 2.0 | estimated11 tok/s | 44/50 |
| 6 | Recursive Flint | 39.8B MoE | Apache 2.0 | estimated68 tok/s | 37/50 |
| 7 | Muse Glimmer 30B slow | 30B | Apache 2.0 | estimated7 tok/s | 42/50 |
| 8 | Nemotron 3.5 Lightning | 30B MoE | OpenMDW | estimated51 tok/s | 36/50 |
| 9 | Gemma 4 26B-A4B | 26B MoE | Apache 2.0 | estimated59 tok/s | 35/50 |
| 10 | MiniCPM-V 4.7 35B-A3B | 35.2B MoE | Apache 2.0 | estimated54 tok/s | 35/50 |
| 11 | Gemma 4 31B slow | 31B | Apache 2.0 | estimated9 tok/s | 40/50 |
| 12 | North Mini Code 1.0 | 30.5B MoE | Apache 2.0 | estimated42 tok/s | 36/50 |
Showing the top 12 of 58 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 model by its tag (checked on ollama.com, 2026-10-24):
ollama run qwen3.6:35b-a3b · model card →
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 Qwen 3.6-35B-A3B on M2 Pro page for its figures and setup.
The Mac mini M2 Pro (32 GB) tops out at Recursive Flint. 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.
Qwen 3.6-35B-A3B (35B MoE, Apache 2.0) is the best all-round pick at ~71 tok/s (estimated) on the Mac mini M2 Pro. If you want maximum speed, Gemma 4 E2B hits ~114 tok/s (estimated); Qwen3.8-27B is more capable but runs at only ~11 tok/s (estimated) here.
About 58 of the 116 models in the LLMCheck index fit in 32 GB of unified memory, from compact models up to Recursive Flint (39.8B MoE).
No. A dense 70B such as Llama 3.3 70B needs about 44 GB at 4-bit; with 32 GB, stick to models like Qwen 3.6-35B-A3B. For a 70B, look at a 64 GB+ Mac.
32 GB is enough for dense models up to about 32B at 4-bit (the largest in the index that fits is QwQ 32B), and for mixture-of-experts models such as KAT-Coder-V2.5 (~53 tok/s (estimated)). As a rule of thumb a 4-bit model needs about 0.57 GB per billion parameters plus ~2 GB, and macOS needs its own share of memory too. Because Apple Silicon uses unified memory, the same pool serves as system RAM and GPU memory.