---
title: "Can I Run Mistral Small 3.2 24B on a Mac? RAM & Speed by Mac"
canonical: https://llmcheck.net/can-i-run/mistral-small-32-24b/
markdown: https://llmcheck.net/md/can-i-run/mistral-small-32-24b.md
page_type: can-i-run
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). Can I run Mistral Small 3.2 24B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/mistral-small-32-24b/ (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)"
---

# Can I run Mistral Small 3.2 24B on a Mac?

Markdown twin of https://llmcheck.net/can-i-run/mistral-small-32-24b/, 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.

Yes: **Mistral Small 3.2 24B** runs on 43 of the 54 Macs in the LLMCheck index. It needs about **14 GB** at a 4K context, 25 GB at 64K. Smallest current Mac: the **Mac mini M6 24 GB;** cheapest at 15+ tok/s: the **Mac mini M5 Pro 24 GB** ($1,699; ~17 tok/s est.). No measured run yet.

24B, Apache 2.0, by Mistral; minimum 14 GB of unified memory (weights plus a short context). It loads on 43 of the 54 Mac configurations the index ranks; 43 of them hold it within macOS's default GPU memory limit.

## Verdict for every Mac (54 configurations)

Verdicts: **Runs** = fits macOS's default GPU memory limit (at 15+ tok/s where the index has a figure); **Runs, slowly** = fits the default limit, under 15 tok/s; **Over GPU limit** = needs more memory than even the index's safe raised GPU limit leaves: the runtime moves part of it to the CPU or shortens the context (llama.cpp, Ollama), runs it slowly (MLX), or stops with an out-of-memory error; **Doesn't fit** = does not load: the model's minimum RAM is above the Mac's, or it has no Mac runtime. Max context = the longest context that fits with a 16-bit KV cache (within the default limit, or the raised one where marked; an estimate from the model's config.json).

| Mac | Sold | Verdict | Build | tok/s | Provenance | Max context | Raise the limit | Model page |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [MacBook Air M5 16 GB](https://llmcheck.net/best-llm/macbook-air-m5-16gb/) | current | Over GPU limit | Q4_K_M | 8 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [MacBook Air M5 24 GB](https://llmcheck.net/best-llm/macbook-air-m5-24gb/) | current | Runs, slowly | Q4_K_M | 8 | estimated | 26K | — | — |
| [MacBook Air M5 32 GB](https://llmcheck.net/best-llm/macbook-air-m5-32gb/) | current | Runs, slowly | Q4_K_M | 8 | estimated | 69K | — | — |
| [MacBook Air M1 8 GB](https://llmcheck.net/best-llm/macbook-air-m1-8gb/) | refurb | Doesn't fit | — | — | — | — | — | — |
| [MacBook Air M4 16 GB](https://llmcheck.net/best-llm/macbook-air-m4-16gb/) | used | Over GPU limit | Q4_K_M | 7 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [MacBook Air M2 16 GB](https://llmcheck.net/best-llm/macbook-air-m2-16gb/) | refurb | Over GPU limit | Q4_K_M | 6 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [MacBook Air M3 16 GB](https://llmcheck.net/best-llm/macbook-air-m3-16gb/) | refurb | Over GPU limit | Q4_K_M | 6 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [MacBook Air M1 16 GB](https://llmcheck.net/best-llm/macbook-air-m1-16gb/) | refurb | Over GPU limit | Q4_K_M | 4 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [MacBook Air M4 24 GB](https://llmcheck.net/best-llm/macbook-air-m4-24gb/) | used | Runs, slowly | Q4_K_M | 7 | estimated | 15K | — | — |
| [MacBook Air M2 24 GB](https://llmcheck.net/best-llm/macbook-air-m2-24gb/) | refurb | Runs, slowly | Q4_K_M | 6 | estimated | 15K | — | — |
| [MacBook Air M3 24 GB](https://llmcheck.net/best-llm/macbook-air-m3-24gb/) | refurb | Runs, slowly | Q4_K_M | 6 | estimated | 15K | — | — |
| [MacBook Pro M6 16 GB](https://llmcheck.net/best-llm/macbook-pro-m6-16gb/) | current | Over GPU limit | Q4_K_M | 8 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [MacBook Pro M5 Pro 24 GB](https://llmcheck.net/best-llm/macbook-pro-m5-pro-24gb/) | current | Runs | Q4_K_M | 17 | estimated | 26K | — | — |
| [MacBook Pro M6 24 GB](https://llmcheck.net/best-llm/macbook-pro-m6-24gb/) | current | Runs, slowly | Q4_K_M | 9 | estimated | 26K | — | — |
| [MacBook Pro M6 32 GB](https://llmcheck.net/best-llm/macbook-pro-m6-32gb/) | current | Runs, slowly | Q4_K_M | 9 | estimated | 69K | — | — |
| [MacBook Pro M5 Pro 48 GB](https://llmcheck.net/best-llm/macbook-pro-m5-pro-48gb/) | current | Runs | Q4_K_M | 17 | estimated | 128K (full window) | — | — |
| [MacBook Pro M5 Max 64 GB](https://llmcheck.net/best-llm/macbook-pro-m5-max-64gb/) | current | Runs | Q4_K_M | 33 | estimated | 128K (full window) | — | — |
| [MacBook Pro M5 Pro 64 GB](https://llmcheck.net/best-llm/macbook-pro-m5-pro-64gb/) | current | Runs | Q4_K_M | 17 | estimated | 128K (full window) | — | — |
| [MacBook Pro M5 Max 128 GB](https://llmcheck.net/best-llm/macbook-pro-m5-max-128gb/) | current | Runs | Q4_K_M | 33 | estimated | 128K (full window) | — | — |
| [MacBook Pro M3 Max 64 GB](https://llmcheck.net/best-llm/macbook-pro-m3-max-64gb/) | refurb | Runs | Q4_K_M | 22 | estimated | 128K (full window) | — | — |
| [MacBook Pro M3 Max 128 GB](https://llmcheck.net/best-llm/macbook-pro-m3-max-128gb/) | refurb | Runs | Q4_K_M | 22 | estimated | 128K (full window) | — | — |
| [Mac mini M6 16 GB](https://llmcheck.net/best-llm/mac-mini-m6-16gb/) | current | Over GPU limit | Q4_K_M | 8 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [Mac mini M5 Pro 24 GB](https://llmcheck.net/best-llm/mac-mini-m5-pro-24gb/) | current | Runs | Q4_K_M | 17 | estimated | 26K | — | — |
| [Mac mini M6 24 GB](https://llmcheck.net/best-llm/mac-mini-m6-24gb/) | current | Runs, slowly | Q4_K_M | 9 | estimated | 26K | — | — |
| [Mac mini M6 32 GB](https://llmcheck.net/best-llm/mac-mini-m6-32gb/) | current | Runs, slowly | Q4_K_M | 9 | estimated | 69K | — | — |
| [Mac mini M5 Pro 48 GB](https://llmcheck.net/best-llm/mac-mini-m5-pro-48gb/) | current | Runs | Q4_K_M | 17 | estimated | 128K (full window) | — | — |
| [Mac mini M5 Pro 64 GB](https://llmcheck.net/best-llm/mac-mini-m5-pro-64gb/) | current | Runs | Q4_K_M | 17 | estimated | 128K (full window) | — | — |
| [Mac mini M2 Pro 16 GB](https://llmcheck.net/best-llm/mac-mini-m2-pro-16gb/) | refurb | Over GPU limit | Q4_K_M | 11 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [Mac mini M4 16 GB](https://llmcheck.net/best-llm/mac-mini-m4-16gb/) | used | Over GPU limit | Q4_K_M | 7 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [Mac mini M4 Pro 24 GB](https://llmcheck.net/best-llm/mac-mini-m4-pro-24gb/) | used | Runs | Q4_K_M | 15 | estimated | 15K | — | — |
| [Mac mini M4 24 GB](https://llmcheck.net/best-llm/mac-mini-m4-24gb/) | used | Runs, slowly | Q4_K_M | 7 | estimated | 15K | — | — |
| [Mac mini M2 Pro 32 GB](https://llmcheck.net/best-llm/mac-mini-m2-pro-32gb/) | refurb | Runs, slowly | Q4_K_M | 11 | estimated | 47K | — | — |
| [Mac mini M4 Pro 48 GB](https://llmcheck.net/best-llm/mac-mini-m4-pro-48gb/) | used | Runs | Q4_K_M | 15 | estimated | 128K (full window) | — | — |
| [Mac mini M4 Pro 64 GB](https://llmcheck.net/best-llm/mac-mini-m4-pro-64gb/) | used | Runs | Q4_K_M | 15 | estimated | 128K (full window) | — | — |
| [iMac M6 16 GB](https://llmcheck.net/best-llm/imac-m6-16gb/) | current | Over GPU limit | Q4_K_M | 8 | estimated | — (no KV figure yet) | `sudo sysctl iogpu.wired_limit_mb=12288` | — |
| [iMac M6 24 GB](https://llmcheck.net/best-llm/imac-m6-24gb/) | current | Runs, slowly | Q4_K_M | 9 | estimated | 26K | — | — |
| [iMac M6 32 GB](https://llmcheck.net/best-llm/imac-m6-32gb/) | current | Runs, slowly | Q4_K_M | 9 | estimated | 69K | — | — |
| [Mac Studio M5 Max 36 GB](https://llmcheck.net/best-llm/mac-studio-m5-max-36gb/) | current | Runs | Q4_K_M | 25 | estimated | 87K | — | — |
| [Mac Studio M5 Max 48 GB](https://llmcheck.net/best-llm/mac-studio-m5-max-48gb/) | current | Runs | Q4_K_M | 33 | estimated | 128K (full window) | — | — |
| [Mac Studio M5 Max 64 GB](https://llmcheck.net/best-llm/mac-studio-m5-max-64gb/) | current | Runs | Q4_K_M | 33 | estimated | 128K (full window) | — | — |
| [Mac Studio M5 Ultra 96 GB](https://llmcheck.net/best-llm/mac-studio-m5-ultra-96gb/) | current | Runs | Q4_K_M | 63 | estimated | 128K (full window) | — | — |
| [Mac Studio M5 Max 128 GB](https://llmcheck.net/best-llm/mac-studio-m5-max-128gb/) | current | Runs | Q4_K_M | 33 | estimated | 128K (full window) | — | — |
| [Mac Studio M5 Ultra 256 GB](https://llmcheck.net/best-llm/mac-studio-m5-ultra-256gb/) | current | Runs | Q4_K_M | 63 | estimated | 128K (full window) | — | — |
| [Mac Studio M5 Ultra 512 GB](https://llmcheck.net/best-llm/mac-studio-m5-ultra-512gb/) | current | Runs | Q4_K_M | 63 | estimated | 128K (full window) | — | — |
| [Mac Studio M2 Max 32 GB](https://llmcheck.net/best-llm/mac-studio-m2-max-32gb/) | refurb | Runs | Q4_K_M | 22 | estimated | 47K | — | — |
| [Mac Studio M1 Ultra 64 GB](https://llmcheck.net/best-llm/mac-studio-m1-ultra-64gb/) | refurb | Runs | Q4_K_M | 42 | estimated | 128K (full window) | — | — |
| [Mac Studio M4 Max 64 GB](https://llmcheck.net/best-llm/mac-studio-m4-max-64gb/) | used | Runs | Q4_K_M | 30 | estimated | 128K (full window) | — | — |
| [Mac Studio M2 Max 64 GB](https://llmcheck.net/best-llm/mac-studio-m2-max-64gb/) | refurb | Runs | Q4_K_M | 22 | estimated | 128K (full window) | — | — |
| [Mac Studio M1 Ultra 128 GB](https://llmcheck.net/best-llm/mac-studio-m1-ultra-128gb/) | refurb | Runs | Q4_K_M | 42 | estimated | 128K (full window) | — | — |
| [Mac Studio M2 Ultra 128 GB](https://llmcheck.net/best-llm/mac-studio-m2-ultra-128gb/) | refurb | Runs | Q4_K_M | 42 | estimated | 128K (full window) | — | — |
| [Mac Studio M4 Max 128 GB](https://llmcheck.net/best-llm/mac-studio-m4-max-128gb/) | used | Runs | Q4_K_M | 30 | estimated | 128K (full window) | — | — |
| [Mac Studio M2 Ultra 192 GB](https://llmcheck.net/best-llm/mac-studio-m2-ultra-192gb/) | refurb | Runs | Q4_K_M | 42 | estimated | 128K (full window) | — | — |
| [Mac Studio M3 Ultra 256 GB](https://llmcheck.net/best-llm/mac-studio-m3-ultra-256gb/) | used | Runs | Q4_K_M | 43 | estimated | 128K (full window) | — | — |
| [Mac Studio M3 Ultra 512 GB](https://llmcheck.net/best-llm/mac-studio-m3-ultra-512gb/) | refurb | Runs | Q4_K_M | 43 | estimated | 128K (full window) | — | — |

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).

For dense models, the formula’s typical error is about **9%** (the median gap to 75 measured plain-decode runs; it tends to undershoot (median −6%), and an estimate scaled from the model’s own measured run is usually closer; [method](https://llmcheck.net/methodology#typical-error)).

## Measured runs of Mistral Small 3.2 24B

The index holds no published or community run of Mistral Small 3.2 24B yet, so every speed above is an estimate from the memory-bandwidth model. Submit a run: https://llmcheck.net/contribute

## Run it

Ollama tag, verified on ollama.com 2026-11-14: `ollama run mistral-small3.2:24b`

Model card: https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506


## Cite this page

LLMCheck. (2026). Can I run Mistral Small 3.2 24B on a Mac? llmcheck.net. https://llmcheck.net/can-i-run/mistral-small-32-24b/ (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
