The best local LLM for a Mac Studio M5 Max (36 GB) is Qwen 3.6-35B-A3B at 112 tok/s (estimated). With 36 GB of unified memory it runs 45 of the models in the LLMCheck index — from compact options up to 35B-class models. For everyday chat and coding, Qwen 3.6-35B-A3B is the sweet spot. Full ranking below.
Considering this Mac?
Mac Studio M5 Max (36GB) on Amazon → · not sure? the Mac Advisor picks a config →
Ranked by LLMCheck suitability (capability balanced against speed on the M5 Max). 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 →
| # | Model | Size | License | Speed | Capability |
|---|---|---|---|---|---|
| 1 | Qwen 3.6-35B-A3B | 35B | Apache 2.0 | estimated112 tok/s | 38/50 |
| 2 | KAT-Coder-V2.5 | 35B | Apache 2.0 | estimated102 tok/s | 39/50 |
| 3 | Qwen3.8-27B | 27.8B | Apache 2.0 | estimated22 tok/s | 46/50 |
| 4 | Qwen 3.6-27B | 27B | Apache 2.0 | estimated23 tok/s | 44/50 |
| 5 | Nemotron 3.5 Lightning | 30B | OpenMDW | estimated88 tok/s | 36/50 |
| 6 | Gemma 4 26B-A4B | 26B | Apache 2.0 | estimated91 tok/s | 35/50 |
| 7 | Laguna XS 2.1 | 33B | OpenMDW | estimated103 tok/s | 33/50 |
| 8 | Muse Glimmer 30B | 30B | Apache 2.0 | estimated20 tok/s | 42/50 |
| 9 | Gemma 4 31B | 31B | Apache 2.0 | estimated19 tok/s | 40/50 |
| 10 | Nemotron-Cascade 2 | 30B | NVIDIA Open | estimated102 tok/s | 30/50 |
| 11 | Qwen 3.5 35B-A3B | 35B | Apache 2.0 | estimated103 tok/s | 27/50 |
| 12 | GLM-4.7-Flash | 31B | MIT | estimated19 tok/s | 35/50 |
Showing the top 12 of 45 models that fit in 36 GB. See the full leaderboard or all benchmarks.
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:
Find Qwen 3.6-35B-A3B 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 Qwen 3.6-35B-A3B on M5 Max benchmark page for exact settings.
The Mac Studio M5 Max (36 GB) comfortably runs 45 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, Apache 2.0) is the best all-round pick at 112 tok/s (estimated) on the M5 Max. If you want maximum speed, Maple Preview 20B-A1B hits 349 tok/s (estimated); for maximum capability, Qwen3.8-27B still fits in 36 GB.
About 45 of the 91 models in the LLMCheck leaderboard fit in 36 GB of unified memory, from compact models up to Qwen 3.6-35B-A3B (35B).
Not comfortably. A 70B model in Q4 needs ~40–44 GB; with 36 GB you should stick to models up to ~30 GB, such as Qwen 3.6-35B-A3B. For 70B, look at a 48 GB+ Mac.
36 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.