---
title: "Best Local LLMs for MacBook Pro M5 Max 64GB (2026)"
canonical: https://llmcheck.net/best-llm/macbook-pro-m5-max-64gb/
markdown: https://llmcheck.net/md/best-llm/macbook-pro-m5-max-64gb.md
page_type: best-llm-mac
publisher: "LLMCheck (llmcheck.net)"
data_version: 2026-11-18
catalog_verified_through: 2026-11-18
updated: 2026-11-19
license: "CC BY 4.0"
license_url: https://creativecommons.org/licenses/by/4.0/
cite: "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 2026-11-19). CC BY 4.0."
provenance:
  sourced: "Published figure — vendor or press review"
  community: "Linked individual run — blog, forum or submission"
  estimated: "Derived from published bandwidth model (https://llmcheck.net/methodology#estimation)"
---

# Best Local LLMs for the MacBook Pro M5 Max (64 GB)

Markdown twin of https://llmcheck.net/best-llm/macbook-pro-m5-max-64gb/, generated from the LLMCheck dataset (data version 2026-11-18) with the same figures as the page. Every speed names its provenance: **sourced** (a published vendor or press figure), **community** (one person's linked run) or **estimated** (the bandwidth model). LLMCheck is an index and runs no tests of its own. Licence CC BY 4.0: credit "LLMCheck (llmcheck.net)" and link the page.

According to the LLMCheck index (18 November 2026), the best local LLM for a MacBook Pro M5 Max (64 GB) is **Qwen 3.6-35B-A3B** at 130 tok/s community-measured on an M5 Max: the best-ranked model that reaches 15 tok/s on this Mac and has a standard Mac runtime. 77 of the 130 models in the index fit in 64 GB; 69 of them reach 15 tok/s here.

## This Mac

| Spec | Value |
| --- | --- |
| Unified memory | 64 GB |
| Memory bandwidth | 614 GB/s |
| Models that fit | 77 of 130 |
| Top speed | 285 tok/s (estimated) — LFM3-1.7B |
| Status | sold new by Apple |
| Price | $5,099 new (Apple list price, checked 2026-11-14) |

## Top 3 picks for the MacBook Pro M5 Max (64 GB)

- **Best overall: [Qwen 3.6-35B-A3B](https://llmcheck.net/models/qwen-36-35b-a3b-on-m5-max/)** — 130 tok/s (community); 35B MoE, Apache 2.0, capability 38/50; agent-ready at 64K
- **Fastest: [LFM3-1.7B](https://llmcheck.net/models/lfm3-17b-on-m5-max/)** — 285 tok/s (estimated); 1.73B, LFM Open, capability 17/50; agent-ready at 64K
- **Most capable: [Qwen3.8-27B](https://llmcheck.net/models/qwen38-27b-on-m5-max/)** — 31 tok/s (community); 27.8B, Apache 2.0, capability 46/50; agent-ready at 64K

## Every model ranked for a MacBook Pro M5 Max (64 GB) (top 12 of 77)

Ranked by LLMCheck suitability: capability plus min(15, tok/s × 0.12) on the M5 Max (614 GB/s). Speeds are per-config figures for this Mac; a measured figure is the chip's run.

| # | Model | Size | License | tok/s | Provenance | Quant | 64K context | Capability | Note |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | [Qwen 3.6-35B-A3B](https://llmcheck.net/models/qwen-36-35b-a3b-on-m5-max/) | 35B MoE | Apache 2.0 | 130 | community | 4-bit | agent-ready (~26 GB of 56 GB usable) | 38/50 | — |
| 2 | [Recursive Flint](https://llmcheck.net/models/recursive-flint-on-m5-max/) | 39.8B MoE | Apache 2.0 | 123 | community | 4-bit | agent-ready (~22 GB of 56 GB usable) | 37/50 | — |
| 3 | [North Mini Code 1.0](https://llmcheck.net/models/north-mini-code-10-on-m5-max/) | 30.5B MoE | Apache 2.0 | 120 | community | 4-bit | agent-ready (~23 GB of 56 GB usable) | 36/50 | — |
| 4 | [Nemotron 3.5 Lightning](https://llmcheck.net/models/nemotron-35-lightning-on-m5-max/) | 30B MoE | OpenMDW | 117 | community | Q4_0 | agent-ready (~19 GB of 56 GB usable) | 36/50 | — |
| 5 | [LFM2.5-24B-A2B](https://llmcheck.net/models/lfm25-24b-a2b-on-m5-max/) | 24B MoE | LFM Open | 184 | sourced | Q4_K_M | agent-ready (~19 GB of 56 GB usable) | 35/50 | — |
| 6 | [Qwen3.8-27B](https://llmcheck.net/models/qwen38-27b-on-m5-max/) | 27.8B | Apache 2.0 | 31 | community | 4-bit | agent-ready (~24 GB of 56 GB usable) | 46/50 | — |
| 7 | [KAT-Coder-V2.5](https://llmcheck.net/models/kat-coder-v25-on-m5-max/) | 35B MoE | Apache 2.0 | 89 | community | OptiQ-4bit | agent-ready (~26 GB of 56 GB usable) | 39/50 | — |
| 8 | [Nanbeige4.3-33B](https://llmcheck.net/models/nanbeige43-33b-on-m5-max/) | 33.1B | Apache 2.0 | 25 | community | oQ4e | agent-ready (~31 GB of 56 GB usable) | 46/50 | — |
| 9 | [Raon-1 mini preview](https://llmcheck.net/models/raon-1-mini-preview-on-m5-max/) | 28.8B MoE | Apache 2.0 | 123 | estimated | Q4_K_M | agent-ready (~20 GB of 56 GB usable) | 34/50 | — |
| 10 | [Ling-3.0-flash-VL](https://llmcheck.net/models/ling-30-flash-vl-on-m5-max/) | 124B MoE | MIT | 53 | estimated | Q4_K_M | needs ~57 GB | 42/50 | raise GPU limit: needs about 56 GB; macOS lets the GPU use ~51.8 GB of 64 GB by default. sudo sysctl iogpu.wired_limit_mb=57344 raises it to 56 GB until the next restart |
| 11 | GLM-4.7-Flash | 31B MoE | MIT | 107 | estimated | Q4_K_M | agent-ready (~22 GB of 56 GB usable) | 35/50 | — |
| 12 | [Gemma 4 26B-A4B](https://llmcheck.net/models/gemma-4-26b-a4b-on-m5-max/) | 26B MoE | Apache 2.0 | 107 | sourced | Q4_K_M | agent-ready (~20 GB of 56 GB usable) | 35/50 | — |

Provenance: **sourced** = Published figure — vendor or press review; **community** = Linked individual run — blog, forum or submission; **estimated** = Derived from published bandwidth model (https://llmcheck.net/methodology#estimation).

## Context

A model is agent-ready at 64K when its weights plus a 65,536-token 16-bit KV cache 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); an estimate from each model's config.json, not a measurement. A q8 KV cache halves the cache part. **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 →](https://llmcheck.net/methodology#gpu-limit)

Estimated figures come from the bandwidth formula; against 233 measured runs its typical error is ±9% for dense models, ±15% for small MoEs (≤40B total) and ±34% for large MoEs (mostly below the measured figure). [How the error is computed →](https://llmcheck.net/methodology#typical-error)

## Quick start: Qwen 3.6-35B-A3B on the MacBook Pro M5 Max

Ollama tag, verified on ollama.com 2026-11-14: `ollama run qwen3.6:35b-a3b`

Model card: https://huggingface.co/Qwen/Qwen3.6-35B-A3B · Figures and setup: https://llmcheck.net/models/qwen-36-35b-a3b-on-m5-max/

## Related

- MacBook Pro M5 Max (128 GB): 93 models fit — https://llmcheck.net/md/best-llm/macbook-pro-m5-max-128gb.md
- Best local LLM for every 64 GB Mac — https://llmcheck.net/md/best-llm/by-ram.md
- Every Mac — https://llmcheck.net/md/best-llm.md
- Full leaderboard — https://llmcheck.net/md/leaderboard.md


## Cite this page

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 2026-11-19). CC BY 4.0.

How to cite: https://llmcheck.net/cite · Open data (CSV, JSON): https://llmcheck.net/data/ · Every Markdown mirror: https://llmcheck.net/md/index.md
