---
title: "Best Local LLMs for Mac mini M4 Pro 24GB (2026)"
canonical: https://llmcheck.net/best-llm/mac-mini-m4-pro-24gb/
markdown: https://llmcheck.net/md/best-llm/mac-mini-m4-pro-24gb.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 Mac mini M4 Pro (24 GB). llmcheck.net. https://llmcheck.net/best-llm/mac-mini-m4-pro-24gb/ (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 Mac mini M4 Pro (24 GB)

Markdown twin of https://llmcheck.net/best-llm/mac-mini-m4-pro-24gb/, 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 Mac mini M4 Pro (24 GB) is **Qwen 3.6-35B-A3B** at ~74 tok/s estimated: the best-ranked model that reaches 15 tok/s on this Mac and has a standard Mac runtime. 63 of the 130 models in the index fit in 24 GB; 50 of them reach 15 tok/s here.

## This Mac

| Spec | Value |
| --- | --- |
| Unified memory | 24 GB |
| Memory bandwidth | 273 GB/s |
| Models that fit | 63 of 130 |
| Top speed | 198 tok/s (estimated) — LFM3-1.7B |
| Status | no longer sold new (used / refurbished) |
| Price | about $1,399 used (no longer sold new) |

## Top 3 picks for the Mac mini M4 Pro (24 GB)

- **Best overall: Qwen 3.6-35B-A3B** — 74 tok/s (estimated); 35B MoE, Apache 2.0, capability 38/50; raise GPU limit
- **Fastest: LFM3-1.7B** — 198 tok/s (estimated); 1.73B, LFM Open, capability 17/50; agent-ready at 64K
- **Most capable (slow): [Qwen3.8-27B](https://llmcheck.net/models/qwen38-27b-on-m4-pro/)** — 13 tok/s (estimated); 27.8B, Apache 2.0, capability 46/50; raise GPU limit

## Every model ranked for a Mac mini M4 Pro (24 GB) (top 12 of 63)

Ranked by LLMCheck suitability: capability plus min(15, tok/s × 0.12) on the M4 Pro (273 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 | 35B MoE | Apache 2.0 | 74 | estimated | Q4_K_M | needs ~26 GB | 38/50 | raise GPU limit: needs about 24 GB by the catalog's build; macOS lets the GPU use ~16 GB of 24 GB by default. A published run's build peaked at 19.4 GB, inside the 20 GB that sudo sysctl iogpu.wired_limit_mb=20480 allows until the next restart — at a short context only |
| 2 | [Qwen3.8-27B](https://llmcheck.net/models/qwen38-27b-on-m4-pro/) | 27.8B | Apache 2.0 | 13 | estimated | Q4_K_M | needs ~24 GB | 46/50 | slow (under 15 tok/s); raise GPU limit: needs about 19 GB; macOS lets the GPU use ~16 GB of 24 GB by default. sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB until the next restart |
| 3 | Nanbeige4.3-33B | 33.1B | Apache 2.0 | 11 | estimated | Q4_K_M | needs ~31 GB | 46/50 | slow (under 15 tok/s); raise GPU limit (macOS 15): needs about 17 GB; macOS lets the GPU use ~16 GB of 24 GB by default on macOS 15 and earlier (~17.8 GB on macOS 26 and later, enough). sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB until the next restart |
| 4 | KAT-Coder-V2.5 | 35B MoE | Apache 2.0 | 66 | estimated | Q4_K_M | needs ~26 GB | 39/50 | over GPU limit: needs about 24 GB; macOS lets the GPU use ~16 GB of 24 GB by default, and a safe raise reaches 20 GB (leaving 4 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 | [Recursive Flint](https://llmcheck.net/models/recursive-flint-on-m4-pro/) | 39.8B MoE | Apache 2.0 | 80 | estimated | 3.8 bpw | needs ~22 GB | 37/50 | raise GPU limit: needs about 20 GB; macOS lets the GPU use ~16 GB of 24 GB by default. sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB until the next restart |
| 6 | LFM2.5-24B-A2B | 24B MoE | LFM Open | 90 | estimated | Q4_K_M | agent-ready (~19 GB of 20 GB usable) | 35/50 | raise GPU limit (macOS 15): needs about 17 GB; macOS lets the GPU use ~16 GB of 24 GB by default on macOS 15 and earlier (~17.8 GB on macOS 26 and later, enough). sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB until the next restart |
| 7 | Qwen 3.6-27B | 27B | Apache 2.0 | 14 | estimated | Q4_K_M | needs ~23 GB | 44/50 | slow (under 15 tok/s); raise GPU limit: needs about 18 GB; macOS lets the GPU use ~16 GB of 24 GB by default. sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB until the next restart |
| 8 | Nemotron 3.5 Lightning | 30B MoE | OpenMDW | 67 | estimated | Q4_K_M | agent-ready (~19 GB of 20 GB usable) | 36/50 | raise GPU limit: needs about 18 GB; macOS lets the GPU use ~16 GB of 24 GB by default. sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB until the next restart |
| 9 | North Mini Code 1.0 | 30.5B MoE | Apache 2.0 | 65 | estimated | Q4_K_M | needs ~23 GB | 36/50 | over GPU limit: needs about 21 GB; macOS lets the GPU use ~16 GB of 24 GB by default, and a safe raise reaches 20 GB (leaving 4 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 | [Gemma 4 26B-A4B](https://llmcheck.net/models/gemma-4-26b-a4b-on-m4-pro/) | 26B MoE | Apache 2.0 | 72 | estimated | Q4_K_M | agent-ready (~20 GB of 20 GB usable) | 35/50 | raise GPU limit: needs about 18 GB; macOS lets the GPU use ~16 GB of 24 GB by default. sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB until the next restart |
| 11 | [Muse Glimmer 30B](https://llmcheck.net/models/muse-glimmer-30b-on-m4-pro/) | 30B | Apache 2.0 | 10 | community | Q4_K_M | agent-ready (~19 GB of 20 GB usable) | 42/50 | slow (under 15 tok/s); raise GPU limit: needs about 18 GB; macOS lets the GPU use ~16 GB of 24 GB by default. sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB until the next restart |
| 12 | GLM-4.7-Flash | 31B MoE | MIT | 68 | estimated | Q4_K_M | needs ~22 GB | 35/50 | raise GPU limit: needs about 18 GB; macOS lets the GPU use ~16 GB of 24 GB by default. sudo sysctl iogpu.wired_limit_mb=20480 raises it to 20 GB until the next restart |

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 20 GB this Mac's GPU can use with the limit raised (33 of the 58 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 16 GB of this Mac’s 24 GB by default on macOS 15 and earlier, and about 17.8 GB on macOS 26 and later. Of the 63 models that fit, 25 need more than that at a short prompt: 17 need a raised limit and are tagged raise GPU limit (Qwen 3.6-35B-A3B and Gemma 4 31B only past the safe setting below, as measured runs on this much memory show); 8 need more than even the raised limit and are tagged over GPU limit. `sudo sysctl iogpu.wired_limit_mb=20480` raises it to 20 GB, leaving 4 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 163 measured runs its typical error is ±9% for dense models and ±15% for small MoEs (≤40B total). [How the error is computed →](https://llmcheck.net/methodology#typical-error)

## Quick start: Qwen 3.6-35B-A3B on the Mac mini M4 Pro

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

## Related

- Mac mini M4 Pro (48 GB): 71 models fit — https://llmcheck.net/md/best-llm/mac-mini-m4-pro-48gb.md
- Mac mini M4 Pro (64 GB): 77 models fit — https://llmcheck.net/md/best-llm/mac-mini-m4-pro-64gb.md
- Best local LLM for every 24 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 Mac mini M4 Pro (24 GB). llmcheck.net. https://llmcheck.net/best-llm/mac-mini-m4-pro-24gb/ (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
