Intermediate 13 minMac mini

Mac mini M5 Pro and M6: which local AI to choose ?

An open laptop casts green light across a dark desk.
Direct response

There is no Mac mini M5 with the base M5 chip: since Apple's announcement on August 25, 2026, the Mac mini has been sold with the M6 chip (from €1,049, 16 to 32 GB) or the M5 Pro (from €1,999, 24 to 64 GB, 307 GB/s). For local AI, the M6 with 24 or 32 GB runs models with 27 to 35 billion parameters at Q4; the M5 Pro with 64 GB handles a dense 70B or an 80-billion-parameter MoE, while 48 GB is just barely enough for a 70B.

The rumored "Mac mini M5" never came out: Apple went from the Mac mini M4 to the Mac mini M6, with a high-end M5 Pro variant. Here you'll find the lineup and official prices, how much memory to choose for the AI models you're targeting, the speed ceiling to expect, and installation, so you can decide which configuration to buy.

Choosing a machine? Our picks by budget →

By Mohamed Meguedmi·Update 2026-11-20·Tested on Windows, macOS, and Linux
Recommended hardware

Buying alternative for this guide: Mac mini M5 Pro (24GB / 512GB).

Why this choice? Our complete guide on Mac mini M5 Pro (24GB / 512GB) →

Compare all options by budget, from €800 to €3,500 →

Small budget: RTX 5060 · Large models: RTX 5090 · Mac Studio.

On the go: which laptop for local AI →

Affiliate links — commission possible at no extra cost to you. As an Amazon Associate, BestLLMfor earns from qualifying purchases.

#Does the Mac mini M5 exist?

No, Apple has never sold a Mac mini with the base M5 chip. Apple's August 25, 2026 press release introduces a new Mac mini in two versions, with the M6 chip or the M5 Pro chip, and compares it to "the previous Mac mini with M4 chip." Preorders opened on August 25, and sales began on September 22, 2026.

The Mac mini is Apple's compact desktop computer, sold without a display or keyboard. According to its spec sheet, the 2026 model measures 12.7 cm on each side and 5 cm tall, and its maximum continuous power draw is 155 W. Apple pitches the M5 Pro version as an "always-on" desktop "to power AI agents."

The M5 chip does exist: Apple announced it on October 15, 2025, for the 14-inch MacBook Pro, iPad Pro, and Apple Vision Pro, with 153 GB/s of memory bandwidth, 30% more than the M4 according to Apple. The "M5 Mac mini for early 2026" was only a rumor.

i
M6 and M5 Pro: not the same generation
The M6 chip powers the three entry-level Mac mini configurations, and the M5 Pro powers the fourth. For local AI, the M5 Pro keeps the edge: 307 GB/s of memory bandwidth versus 153 to 170 GB/s, and up to 64 GB of memory.

#Which Mac mini M6 and M5 Pro models does Apple sell, and at what price?

The complete kit for making the most of local AI on your Mac.

Benefit from our experience and a guided path to choose the right tools for your Mac and use your AI every day.

  • Lifetime online access
  • PDF + files
  • Refunded within 30 days

Apple sells the Mac mini M6 starting at €1,049 and the Mac mini M5 Pro starting at €1,999, the retail prices announced by Apple in its August 25, 2026 press release. On the Education Store, starting prices are €929 and €1,879.

Mac mini lineup per the Apple spec sheet, accessed November 18, 2026
VersionCPU / GPUUnified memoryBandwidthStarting price
Mac mini M612 cores / 12 cores16 GB (24 or 32 GB optional)153 GB/s with 16 GB, 170 GB/s with 24 and 32 GB1 049 €
Mac mini M5 Pro15 cores / 16 cores (optional 18 / 20 cores)24 GB (48 or 64 GB optional)307 GB/s1 999 €

The Mac mini M5 Pro also has three Thunderbolt 5 ports (up to 120 Gb/s), versus three Thunderbolt 4 ports on the M6. For storage, the Mac mini M6 starts at a 256 GB SSD (512 GB on its two other configurations), configurable up to 2 TB; the Mac mini M5 Pro starts at 512 GB, configurable up to 8 TB.

#How much memory does a Mac mini need for local AI?

On a Mac mini, the amount of unified memory determines the size of the largest AI model you can load. Unified memory is a single pool of memory shared by the CPU and the GPU: it serves as both system RAM and video memory.

Q4 quantization
Compressing a model's weights to about 4 bits, which cuts the required memory by roughly a factor of four compared with the original 16-bit weights, with a moderate loss in quality.
Approximate size at Q4
A 7- to 8-billion-parameter model takes up about 5 GB, a 14B about 9 GB, a 32B about 19 to 20 GB, and a 70B about 40 GB, weights alone. Context (the conversation length) comes on top of that.
Headroom for macOS
macOS, your browser, and your apps also use unified memory. A conservative rule of thumb: keep at least 6 to 8 GB free on top of the model, more with a long context.
MoE model
A mixture-of-experts (MoE) model stores all of its parameters in memory but reads only some of them per token. The name often tells you: "35B-A3B" means 35 billion total, about 3 billion active.

What this means for the Mac mini M6: 12 to 14 billion parameters at most with 16 GB, 27 billion at Q4 with 24 GB, and 30 to 35 billion with 32 GB. The site's memory calculator refines these figures.

#Which AI models run on a Mac mini M6 or M5 Pro?

The 24 or 32 GB Mac mini M6 runs 2026's good general-purpose models, such as Qwen 3.8 27B or Gemma 4 31B, and the 64 GB Mac mini M5 Pro handles models up to 80 billion parameters in Q4. The table below matches each configuration's memory against the Q4 size of the models in the quelllm catalog.

Suitable models by Mac mini configuration (Q4 sizes from the quelllm catalog, weights only; estimated speed ceiling, not measured)
ConfigurationRecommended models (Q4 size)Estimated generation ceiling
M6, 16 GB, 153 GB/sGemma 4 12B (7 GB), Qwen 3 8B (5 GB)about 22 tokens/s for Gemma 4 12B
M6, 24 GB, 170 GB/sQwen 3.8 27B (16 GB), Gemma 4 26B-A4B MoE (16 GB), gpt-oss 20B (13 GB)about 11 tokens/s for Qwen 3.8 27B
M6, 32 GB, 170 GB/sGemma 4 31B (18 GB), Qwen 3.6 35B-A3B (21 GB)about 9 tokens/s for Gemma 4 31B
M5 Pro, 24 GB, 307 GB/sQwen 3.8 27B (16 GB), gpt-oss 20B (13 GB)about 19 tokens/s for Qwen 3.8 27B
M5 Pro, 48 GB, 307 GB/sGemma 4 31B (18 GB) with long context; dense 70B models (about 40 GB) at the limit: short context, and raise the wired memory limit if neededabout 8 tokens/s for a dense 70B
M5 Pro, 64 GB, 307 GB/sQwen3-Coder-Next 80B-A3B (48 GB; raise the wired memory limit if needed), 70B models with comfortable contextsignificantly higher for the MoE with 3B active parameters (not estimated here), about 8 tokens/s for a dense 70B

What doesn't fit: gpt-oss 120B (70 GB in Q4), Mistral Small 4 (72 GB), or Qwen3.8 Flash Next 125B-A6B (72 GB) exceed the 64 GB of the top-spec Mac mini M5 Pro.

#Is the Mac mini M5 Pro really 4 times faster at AI?

The "up to 4x faster" figure for the Mac mini M5 Pro versus the M4 Pro refers to prompt processing, not the speed at which the response is generated. According to Apple's footnote, the July 2026 test measures time to first token, using an 8,000-token prompt, a 14-billion-parameter 4-bit model, and LM Studio 0.4.18+1. It compares a high-end prototype Mac mini M5 Pro (18-core CPU, 20-core GPU, 64 GB) against a 64 GB Mac mini M4 Pro: the €1,999 base configuration was not measured.

Prompt processing (prefill) depends on compute power: the Neural Accelerators built into each GPU core of the M6 and M5 Pro chips speed it up significantly, which matters when you summarize a long document or feed an agent. For the Mac mini M6, Apple claims up to 4.8 times faster performance than the Mac mini M4 on the same type of test, with both machines configured with 32 GB.

Generating response tokens depends mainly on memory bandwidth. Estimated theoretical ceiling: bandwidth divided by the size of the weights read for each token, which for Qwen 3.8 27B (16 GB in Q4) works out to about 307 ÷ 16 ≈ 19 tokens/s on the M5 Pro and 170 ÷ 16 ≈ 11 tokens/s on the 24 GB M6. Real-world speed stays below that; no independent benchmarks of these Mac mini models are cited here.

#How do you set up local AI on a Mac mini M6 or M5 Pro?

A Mac mini M6 or M5 Pro runs Ollama, LM Studio, and MLX without any special configuration, since all three tools support the GPU on Apple chips. The Ollama documentation requires macOS Sonoma 14 or later; the LM Studio documentation requires macOS 14.0 at minimum and recommends 16 GB of memory or more. Its chip list stops at the M4, but Apple has measured LM Studio itself on the Mac mini M6 and M5 Pro.

  1. 01
    Choose the tool
    LM Studio for a graphical interface; Ollama for the terminal and a local API on port 11434; mlx-lm to use MLX directly, Apple's library for its chips.
  2. 02
    Install Ollama
    Download the app from ollama.com and drag it into the Applications folder, or run the official install script shown below in the macOS Terminal.
  3. 03
    Load a model that fits your memory
    From the configuration table, choose a model whose Q4 size leaves at least 6 to 8 GB free. On a 16 GB Mac mini M6, start with a model of 8 to 12 billion parameters.
  4. 04
    Verify that the GPU is working
    In Ollama, the ollama ps command shows whether the model is loaded on the GPU or partly on the CPU. In Activity Monitor, on the Memory tab, red memory pressure indicates that the model or context is too large.
macOS: install Ollama (official script)
curl -fsSL https://ollama.com/install.sh | sh
macOS: install mlx-lm and generate your first text
pip install mlx-lm
mlx_lm.generate --prompt "How tall is Mt Everest?"

For a very large model on a 48 or 64 GB Mac mini M5 Pro, the mlx-lm documentation notes that a model close to total memory can be slow, and that it often speeds up when you raise the wired memory limit (macOS 15 or later). The value N, in megabytes, must exceed the model size and stay below the machine's memory.

macOS 15 or later: raise the wired memory limit (N in MB)
sudo sysctl iogpu.wired_limit_mb=N
!
Wired memory limit: handle with care
Setting N too close to total memory starves macOS and your apps of memory. Example for a 64 GB Mac mini M5 Pro and a 48 GB model: a value around 52,000 MB follows the mlx-lm rule while leaving about 12 GB for the rest of the system (rough estimate).

#Which Mac mini should you choose in 2026 for local AI?

For local AI in 2026, choosing a Mac mini comes down to memory first: a Mac mini M6 with 24 or 32 GB for a personal assistant running a 27 to 35 billion parameter model, and a Mac mini M5 Pro with 64 GB for coding, agents, and 70 to 80 billion parameter models.

Getting started with local AI: small models
Mac mini M6 with 16 GB, starting at €1,049. Limit: models of 12 to 14 billion parameters at most, with moderate context.
Everyday assistant, writing, documents
Mac mini M6 with 24 or 32 GB. Qwen 3.8 27B or Gemma 4 31B fit with headroom left for macOS.
Development, always-on agents
Mac mini M5 Pro with 48 or 64 GB. With 307 GB/s versus 170 GB/s, the estimated generation ceiling is about 1.8 times higher than with the M6 on the same model, and 64 GB can hold Qwen3-Coder-Next 80B-A3B.
Models over 64 GB
A Mac mini alone isn't enough: a Mac Studio, a cluster of Mac minis connected over Thunderbolt 5 (a solution cited by Apple), or a machine with 128 GB of memory.
Tight budget
A used Mac mini M4 or M4 Pro follows the same logic: check how much memory it has first.

Buy now or wait: the Mac mini M6 and M5 Pro, on sale since September 22, 2026, was still the generation listed on Apple's tech specs page as of November 18, 2026. Either way, invest in memory first, since it's fixed when you order; storage matters less, because Ollama can store models on another drive.

Frequently asked questions
When was Apple's M5 chip released?+
Apple announced the M5 chip on October 15, 2025, in the 14-inch MacBook Pro, the iPad Pro, and the Apple Vision Pro. The Mac mini never got the base M5: its M6 and M5 Pro versions, announced on August 25, 2026, have been on sale since September 22, 2026.
How much does the Mac mini M5 Pro cost?+
The Mac mini M5 Pro costs €1,999 at the starting price announced by Apple on August 25, 2026, with a 15-core CPU, 16-core GPU, 24 GB of unified memory, and a 512 GB SSD. The Education Store offers it from €1,879. The 48 or 64 GB options and the 18-core CPU increase the price.
Is a 16 GB Mac mini M6 enough for local AI?+
The 16 GB Mac mini M6 is enough to get started with local AI using 8 to 12 billion parameter models in Q4, such as Gemma 4 12B (7 GB). For a 27 billion parameter model like Qwen 3.8 27B (16 GB in Q4), you need to move up to 24 GB, because macOS also takes up part of the memory.
Can you add memory to a Mac mini after purchase?+
No, the unified memory of a Mac mini M6 or M5 Pro is integrated into the chip and chosen when you order: 16, 24, or 32 GB on the M6, and 24, 48, or 64 GB on the M5 Pro, according to Apple's tech specs. Storage, on the other hand, can be expanded with an external SSD.
Mac mini M5 Pro or Mac Studio for local AI?+
The Mac mini M5 Pro tops out at 64 GB of unified memory and 307 GB/s, enough for 70 to 80 billion-parameter models at Q4. Beyond that, or to generate faster with large dense models, a Mac Studio with more memory and bandwidth becomes the right choice.
Does local AI on a Mac mini send my data online?+
No: with Ollama, LM Studio, or mlx-lm, the model runs on the Mac mini and your text stays on the machine once the model is downloaded. The Apple Intelligence and Siri AI features in macOS 27 are a separate matter: Apple states that some of them rely on server-side models.

#Sources and verification as of November 18, 2026

Lineup, specifications, dates, and prices were collected on November 18, 2026 from the Apple press release and spec sheet; software requirements come from the Ollama, LM Studio, and mlx-lm documentation. Prices and options may change; speed ceilings are calculated estimates, not measurements.

Did this guide help you?

Feedback, an error, or a clarification? Let us know—it improves the guide for everyone.

Prices in euros (€) are French market prices including VAT, as checked by BestLLMfor. US prices differ: the Amazon buttons show the current US price.