The best local LLM for a MacBook Pro M5 Max (64 GB) is Qwen 3.6-35B-A3B at 130 tok/s (community run). Its 64 GB fits 77 of the 130 models in the LLMCheck index, up to 124B-class. For everyday chat and coding, Qwen 3.6-35B-A3B is the sweet spot.
Considering this Mac?
MacBook Pro M5 Max (64 GB): build-to-order from Apple · MacBook Pro M5 Max (36 GB) 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, has a standard Mac runtime and fits the GPU memory limit (raised if need be), 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 | 64K context | Capability |
|---|---|---|---|---|---|---|
| 1 | Qwen 3.6-35B-A3B | 35B MoE | Apache 2.0 | community130 tok/s | agent-ready | 38/50 |
| 2 | Recursive Flint | 39.8B MoE | Apache 2.0 | community123 tok/s | agent-ready | 37/50 |
| 3 | North Mini Code 1.0 | 30.5B MoE | Apache 2.0 | community120 tok/s | agent-ready | 36/50 |
| 4 | Nemotron 3.5 Lightning | 30B MoE | OpenMDW | community117 tok/s | agent-ready | 36/50 |
| 5 | LFM2.5-24B-A2B | 24B MoE | LFM Open | sourced184 tok/s | agent-ready | 35/50 |
| 6 | Qwen3.8-27B | 27.8B | Apache 2.0 | community31 tok/s | agent-ready | 46/50 |
| 7 | KAT-Coder-V2.5 | 35B MoE | Apache 2.0 | community89 tok/s | agent-ready | 39/50 |
| 8 | Nanbeige4.3-33B | 33.1B | Apache 2.0 | community25 tok/s | agent-ready | 46/50 |
| 9 | Raon-1 mini preview | 28.8B MoE | Apache 2.0 | estimated123 tok/s | agent-ready | 34/50 |
| 10 | Ling-3.0-flash-VL raise GPU limit | 124B MoE | MIT | estimated53 tok/s | 42/50 | |
| 11 | GLM-4.7-Flash | 31B MoE | MIT | estimated107 tok/s | agent-ready | 35/50 |
| 12 | Gemma 4 26B-A4B | 26B MoE | Apache 2.0 | sourced107 tok/s | agent-ready | 35/50 |
Showing the top 12 of 77 models that fit in 64 GB. See the full leaderboard or all benchmarks.
Context: “fits” means the weights at a short prompt. Coding agents (Claude Code, OpenCode, Codex CLI) hold 64K tokens or more, and every token adds KV cache: agent-ready marks a model whose weights plus a 64K-token 16-bit KV cache still fit in the 56 GB this Mac’s GPU can use with the limit raised (60 of the 70 models here with a KV figure). That is an estimate from each model’s config.json, not a measurement; a q8 KV cache halves the cache part, and — means the index has no KV figure for the model yet. The GPU memory limit below applies on top.
GPU memory limit: macOS lets the GPU use about 51.8 GB of this Mac’s 64 GB by default (macOS 26 and later, the only macOS it runs). Of the 77 models that fit, 5 need more than that at a short prompt: 2 need a raised limit and are tagged raise GPU limit; 3 need more than even the raised limit and are tagged over GPU limit. sudo sysctl iogpu.wired_limit_mb=57344 raises it to 56 GB, leaving 8 GB for macOS, until the Mac restarts (sudo sysctl iogpu.wired_limit_mb=0 restores the default). How the limit is read →
The fastest way to get started is Ollama. Install it, then pull the model by its tag (checked on ollama.com, 2026-11-14):
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.
Twice as fast: no Mac in the index runs Qwen 3.6-35B-A3B at twice this Mac’s community130 tok/s; the fastest figure is the Mac Studio M5 Ultra (96 GB) at community153 tok/s, $5,499 new (Apple list price, checked 2026-11-14): build-to-order from Apple (Amazon does not stock this configuration).
For less: the cheapest Mac that still runs Qwen 3.6-35B-A3B at 15+ tok/s is the MacBook Air M2 (24 GB) at estimated~43 tok/s, about $850 refurbished or used: search Amazon Renewed listings →. New: the Mac mini M6 (24 GB) at community59 tok/s, $1,099 new (Apple list price, checked 2026-11-14): Mac mini M6 (24GB) on Amazon →.
Speeds are each Mac’s own figure from the index, with its provenance mark. Prices come from data/macs.json: Apple’s list price for a new Mac (dated), an approximate street price for a used or refurbished one. Amazon stock checked 2026-11-18. Amazon links are affiliate links: as an Amazon Associate, LLMCheck earns from qualifying purchases.
The MacBook Pro M5 Max (64 GB) runs 77 of the models in the LLMCheck index, led by Qwen 3.6-35B-A3B. This 64 GB configuration is build-to-order from Apple: Amazon does not stock it (it carries the standard 36 GB MacBook Pro M5 Max, with less memory).
As an Amazon Associate, LLMCheck earns from qualifying purchases. Affiliate links cost you nothing extra and never influence our rankings.
LLMCheck. (2026). Best Local LLMs for the MacBook Pro M5 Max (64 GB). llmcheck.net. https://llmcheck.net/best-llm/macbook-pro-m5-max-64gb/ (updated ). CC BY 4.0.
Qwen 3.6-35B-A3B (35B MoE, Apache 2.0) is the best all-round pick at 130 tok/s (community run) on the MacBook Pro M5 Max. If you want maximum speed, LFM3-1.7B hits ~285 tok/s (estimated); for maximum capability, Qwen3.8-27B still fits in 64 GB.
About 77 of the 130 models in the LLMCheck index fit in 64 GB of unified memory, from compact models up to Ling-3.0-flash-VL (124B 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 Ling-3.0-flash-VL (~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.