---
title: "Best Local LLMs for MacBook Pro M3 Max 128GB (2026)"
canonical: https://llmcheck.net/best-llm/macbook-pro-m3-max-128gb/
markdown: https://llmcheck.net/md/best-llm/macbook-pro-m3-max-128gb.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 M3 Max (128 GB). llmcheck.net. https://llmcheck.net/best-llm/macbook-pro-m3-max-128gb/ (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 M3 Max (128 GB)

Markdown twin of https://llmcheck.net/best-llm/macbook-pro-m3-max-128gb/, 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 M3 Max (128 GB) is **Qwen3.8-Flash-Next** at ~35 tok/s estimated: the best-ranked model that reaches 15 tok/s on this Mac and has a standard Mac runtime. 93 of the 130 models in the index fit in 128 GB; 80 of them reach 15 tok/s here.

## This Mac

| Spec | Value |
| --- | --- |
| Unified memory | 128 GB |
| Memory bandwidth | 400 GB/s |
| Models that fit | 93 of 130 |
| Top speed | 255 tok/s (estimated) — LFM3-1.7B |
| Status | no longer sold new (used / refurbished) |
| Price | about $2,600 refurbished or used |

## Top 3 picks for the MacBook Pro M3 Max (128 GB)

- **Best overall: Qwen3.8-Flash-Next** — 35 tok/s (estimated); 125B MoE, Qwen Custom, capability 47/50; raise GPU limit
- **Fastest: LFM3-1.7B** — 255 tok/s (estimated); 1.73B, LFM Open, capability 17/50; agent-ready at 64K
- **Most capable: GLM-5.3-Flash** — 17 tok/s (estimated); 320B MoE, MIT, capability 48/50; over GPU limit

## Every model ranked for a MacBook Pro M3 Max (128 GB) (top 12 of 93)

Ranked by LLMCheck suitability: capability plus min(15, tok/s × 0.12) on the M3 Max (400 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 | Qwen3.8-Flash-Next | 125B MoE | Qwen Custom | 35 | estimated | Q4_K_M | needs ~122 GB | 47/50 | raise GPU limit: needs about 120 GB; macOS lets the GPU use ~96 GB of 128 GB by default; measured runs on 128 GB Macs show it loads with a raised limit. The index's safe raise (sudo sysctl iogpu.wired_limit_mb=114688, 112 GB) is below that need, so those runs left macOS less than 16 GB: quit other apps first |
| 2 | [DeepSeek V4 Flash](https://llmcheck.net/models/deepseek-v4-flash-on-m3-max/) | 284B MoE | MIT | 27 | community | Q2_K | needs ~121 GB | 47/50 | raise GPU limit: needs about 120 GB; macOS lets the GPU use ~96 GB of 128 GB by default; measured runs on 128 GB Macs show it loads with a raised limit. The index's safe raise (sudo sysctl iogpu.wired_limit_mb=114688, 112 GB) is below that need, so those runs left macOS less than 16 GB: quit other apps first |
| 3 | GLM-5.3-Flash | 320B MoE | MIT | 17 | estimated | 3.3 bpw | needs ~129 GB | 48/50 | over GPU limit: needs about 128 GB; macOS lets the GPU use ~96 GB of 128 GB by default, and a safe raise reaches 112 GB (leaving 16 GB for macOS): expect heavy swapping, a CPU split or an out-of-memory error; a smaller quant or a shorter context may fit |
| 4 | DeepSeek V4 Flash Vision-Exp | 305B MoE | MIT | 24 | estimated | 3.2 bpw | needs ~121 GB | 47/50 | over GPU limit: needs about 120 GB; macOS lets the GPU use ~96 GB of 128 GB by default, and a safe raise reaches 112 GB (leaving 16 GB for macOS): expect heavy swapping, a CPU split or an out-of-memory error; a smaller quant or a shorter context may fit |
| 5 | Inkling-Small | 276B MoE | Apache 2.0 | 29 | estimated | 2.8 bpw | agent-ready (~98 GB of 112 GB usable) | 46/50 | runtime caveat: llama.cpp support is the unmerged PR #25731 and stock mlx-lm cannot load it; the MLX builds bundle their own loader. |
| 6 | [KAT-Coder-V2.5](https://llmcheck.net/models/kat-coder-v25-on-m3-max/) | 35B MoE | Apache 2.0 | 84 | estimated | Q4_K_M | agent-ready (~26 GB of 112 GB usable) | 39/50 | — |
| 7 | Qwen 3.6-35B-A3B | 35B MoE | Apache 2.0 | 92 | estimated | Q4_K_M | agent-ready (~26 GB of 112 GB usable) | 38/50 | — |
| 8 | [Qwen3.8-27B](https://llmcheck.net/models/qwen38-27b-on-m3-max/) | 27.8B | Apache 2.0 | 19 | estimated | Q4_K_M | agent-ready (~24 GB of 112 GB usable) | 46/50 | — |
| 9 | Qwen3-235B-A22B | 235B MoE | Apache 2.0 | 17 | estimated | 4.5 bpw | needs ~140 GB | 46/50 | over GPU limit: needs about 128 GB; macOS lets the GPU use ~96 GB of 128 GB by default, and a safe raise reaches 112 GB (leaving 16 GB for macOS): expect heavy swapping, a CPU split or an out-of-memory error; a smaller quant or a shorter context may fit |
| 10 | Nanbeige4.3-33B | 33.1B | Apache 2.0 | 15 | estimated | Q4_K_M | agent-ready (~31 GB of 112 GB usable) | 46/50 | — |
| 11 | Recursive Flint | 39.8B MoE | Apache 2.0 | 89 | estimated | Q4_K_M | agent-ready (~22 GB of 112 GB usable) | 37/50 | — |
| 12 | Ling-3.0-flash-VL | 124B MoE | MIT | 37 | estimated | Q4_K_M | agent-ready (~57 GB of 112 GB usable) | 42/50 | — |

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 112 GB this Mac's GPU can use with the limit raised (76 of the 85 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 96 GB of this Mac’s 128 GB by default on macOS 15 and earlier, and about 107.5 GB on macOS 26 and later. Of the 93 models that fit, 7 need more than that at a short prompt: 2 need a raised limit and are tagged raise GPU limit (Qwen3.8-Flash-Next and DeepSeek V4 Flash only past the safe setting below, as measured runs on this much memory show); 5 need more than even the raised limit and are tagged over GPU limit. `sudo sysctl iogpu.wired_limit_mb=114688` raises it to 112 GB, leaving 16 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: Qwen3.8-Flash-Next on the MacBook Pro M3 Max

No verified Ollama tag in the index; start from the listing: https://ollama.com/search?q=Qwen3.8-Flash-Next

Model card: https://huggingface.co/Qwen/Qwen3.8-Flash-Next

## Related

- MacBook Pro M3 Max (64 GB): 77 models fit — https://llmcheck.net/md/best-llm/macbook-pro-m3-max-64gb.md
- Best local LLM for every 128 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 M3 Max (128 GB). llmcheck.net. https://llmcheck.net/best-llm/macbook-pro-m3-max-128gb/ (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
