The best local LLM for a Mac Studio M5 Max (64 GB) is Qwen 3.6-35B-A3B at 118 tok/s (published figure). Its 64 GB fits 66 of the 111 models in the LLMCheck index, up to 119B-class. For everyday chat and coding, Qwen 3.6-35B-A3B is the sweet spot.
Considering this Mac?
Mac Studio M5 Max (64GB) on Amazon → · not sure? the Mac Advisor picks a config →
Ranked by LLMCheck suitability (capability balanced against speed on the M5 Max); 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 | sourced118 tok/s | 38/50 |
| 2 | North Mini Code 1.0 | 30.5B MoE | Apache 2.0 | community120 tok/s | 36/50 |
| 3 | LFM2.5-24B-A2B | 24B MoE | LFM Open | sourced184 tok/s | 35/50 |
| 4 | KAT-Coder-V2.5 | 35B MoE | Apache 2.0 | community89 tok/s | 39/50 |
| 5 | Nemotron 3.5 Lightning | 30B MoE | OpenMDW | sourced114 tok/s | 36/50 |
| 6 | Qwen3.8-27B | 27.8B | Apache 2.0 | estimated29 tok/s | 46/50 |
| 7 | Gemma 4 26B-A4B | 26B MoE | Apache 2.0 | sourced107 tok/s | 35/50 |
| 8 | Nemotron 3.5 Bolt 74B-A9B | 74B MoE | OpenMDW | community64 tok/s | 40/50 |
| 9 | Qwen 3.6-27B | 27B | Apache 2.0 | estimated30 tok/s | 44/50 |
| 10 | Laguna XS 2.1 | 33B MoE | OpenMDW | estimated117 tok/s | 33/50 |
| 11 | MiniCPM-V 4.7 35B-A3B | 35.2B MoE | Apache 2.0 | community100 tok/s | 35/50 |
| 12 | Muse Glimmer 30B | 30B | Apache 2.0 | sourced27 tok/s | 42/50 |
Showing the top 12 of 66 models that fit in 64 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, 2026-10-17):
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 M5 Max page for its figures and setup.
The Mac Studio M5 Max (64 GB) runs 66 of the models in the LLMCheck index, led by Qwen 3.6-35B-A3B. 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.
Qwen 3.6-35B-A3B (35B MoE, Apache 2.0) is the best all-round pick at 118 tok/s (published figure) on the Mac Studio M5 Max. If you want maximum speed, Gemma 4 E2B hits ~261 tok/s (estimated); for maximum capability, Qwen3.8-27B still fits in 64 GB.
About 66 of the 111 models in the LLMCheck index fit in 64 GB of unified memory, from compact models up to Mistral Small 4 (119B MoE).
Yes. A dense 70B such as Llama 3.3 70B needs about 44 GB at 4-bit, which fits in 64 GB with room for context; the index puts it at 13 tok/s (published figure) on this Mac.
64 GB is enough for dense models up to about 72B at 4-bit (the largest in the index that fits is Qwen 2.5 72B), and for mixture-of-experts models such as Nemotron 3.5 Bolt 74B-A9B (64 tok/s (community run)). 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.