Run AI in-house

Mac mini M6 & M5 Pro – a compact local AI machine for business

Mac mini is the most compact way to start running local AI: language models (LLMs) run directly on a machine in your office — files, contracts and customer data are never sent to any outside service. Unified memory from 16GB to 64GB runs models up to about 76B parameters (estimate, 4-bit quantization), in a machine just 5.0 cm tall with a maximum continuous power draw of 155W.

Genuine, factory-sealedVAT included, VAT invoice issuedAdvice based on the models you need to runMLX, Ollama and LM Studio setup

Prices for all 9 Mac mini M6 & M5 Pro configurations (VAT included)

Mac mini M6 starts at 30.000.000₫, M5 Pro at 57.600.000₫. Each card shows the AI model size it can run — filter by chip, RAM or the model size you need.

Chip
Memory (RAM)
Model size you need
Sort
Mac mini M6 12CPU 12GPU 16GB 256GBM6

Mac mini M6 12CPU 12GPU 16GB 256GB

  • CPU / GPU12 / 12 cores
  • Unified memory16GB
  • Bandwidth153GB/s
  • Storage256GB

Runs models up to ~19B parameters (estimate, 4-bit)

30.000.000₫
VAT included
View details
Mac mini M6 12CPU 12GPU 24GB 256GBM6

Mac mini M6 12CPU 12GPU 24GB 256GB

  • CPU / GPU12 / 12 cores
  • Unified memory24GB
  • Bandwidth170GB/s
  • Storage256GB

Runs models up to ~28B parameters (estimate, 4-bit)

36.600.000₫
VAT included
View details
Mac mini M6 12CPU 12GPU 32GB 256GBM6

Mac mini M6 12CPU 12GPU 32GB 256GB

  • CPU / GPU12 / 12 cores
  • Unified memory32GB
  • Bandwidth170GB/s
  • Storage256GB

Runs models up to ~38B parameters (estimate, 4-bit)

43.200.000₫
VAT included
View details
Mac mini M5 Pro 15CPU 16GPU 24GB 512GBM5 Pro

Mac mini M5 Pro 15CPU 16GPU 24GB 512GB

  • CPU / GPU15 / 16 cores
  • Unified memory24GB
  • Bandwidth307GB/s
  • Storage512GB

Runs models up to ~28B parameters (estimate, 4-bit)

57.600.000₫
VAT included
View details
Mac mini M5 Pro 15CPU 16GPU 48GB 512GBM5 Pro

Mac mini M5 Pro 15CPU 16GPU 48GB 512GB

  • CPU / GPU15 / 16 cores
  • Unified memory48GB
  • Bandwidth307GB/s
  • Storage512GB

Runs models up to ~57B parameters (estimate, 4-bit)

77.400.000₫
VAT included
View details
Mac mini M5 Pro 15CPU 16GPU 64GB 512GBM5 Pro

Mac mini M5 Pro 15CPU 16GPU 64GB 512GB

  • CPU / GPU15 / 16 cores
  • Unified memory64GB
  • Bandwidth307GB/s
  • Storage512GB

Runs models up to ~76B parameters (estimate, 4-bit)

90.600.000₫
VAT included
View details
Mac mini M5 Pro 18CPU 20GPU 24GB 512GBM5 Pro

Mac mini M5 Pro 18CPU 20GPU 24GB 512GB

  • CPU / GPU18 / 20 cores
  • Unified memory24GB
  • Bandwidth307GB/s
  • Storage512GB

Runs models up to ~28B parameters (estimate, 4-bit)

64.200.000₫
VAT included
View details
Mac mini M5 Pro 18CPU 20GPU 48GB 512GBM5 Pro

Mac mini M5 Pro 18CPU 20GPU 48GB 512GB

  • CPU / GPU18 / 20 cores
  • Unified memory48GB
  • Bandwidth307GB/s
  • Storage512GB

Runs models up to ~57B parameters (estimate, 4-bit)

84.000.000₫
VAT included
View details
Mac mini M5 Pro 18CPU 20GPU 64GB 512GBM5 Pro

Mac mini M5 Pro 18CPU 20GPU 64GB 512GB

  • CPU / GPU18 / 20 cores
  • Unified memory64GB
  • Bandwidth307GB/s
  • Storage512GB

Runs models up to ~76B parameters (estimate, 4-bit)

97.200.000₫
VAT included
View details

Prices include VAT. SSD upgrades and 10Gb Ethernet cost extra — choose them on each machine’s detail page. Specifications from apple.com/vn, updated September 24, 2026.

Compare 9 configurations at a glance: RAM, bandwidth and model size

ConfigurationCPU / GPUMemoryBandwidthMax modelPrice
M6 12/12 · 16GB12 / 12 cores16GB153GB/s~19B30.000.000₫
M6 12/12 · 24GB12 / 12 cores24GB170GB/s~28B36.600.000₫
M6 12/12 · 32GB12 / 12 cores32GB170GB/s~38B43.200.000₫
M5 Pro 15/16 · 24GB15 / 16 cores24GB307GB/s~28B57.600.000₫
M5 Pro 15/16 · 48GB15 / 16 cores48GB307GB/s~57B77.400.000₫
M5 Pro 15/16 · 64GB15 / 16 cores64GB307GB/s~76B90.600.000₫
M5 Pro 18/20 · 24GB18 / 20 cores24GB307GB/s~28B64.200.000₫
M5 Pro 18/20 · 48GB18 / 20 cores48GB307GB/s~57B84.000.000₫
M5 Pro 18/20 · 64GB18 / 20 cores64GB307GB/s~76B97.200.000₫

Memory bandwidth determines how fast the machine generates text. GPU core count determines how quickly it processes a long prompt before it starts answering.

How much RAM do you need for each model size?

How much RAM you need to run an LLM locally on Mac mini depends on the model size: from ~19B parameters on the 16GB version to ~76B on the 64GB version. For language models, memory capacity decides whether a model runs at all, and memory bandwidth decides how fast it runs. The table below converts machine memory into the model size it can run.

System memoryAvailable to the modelMax model size (4-bit)Best for
16GB~12GB~19BLocal AI trials, small models, summarizing and drafting short documents
24GB~18GB~28BSmall models for a few users, small-scale internal document Q&A
32GB~24GB~38BAs above, with extra headroom for longer context
48GB~36GB~57BMid-size models, an internal document Q&A assistant for a small team
64GB~48GB~76BLarger mid-size models — the highest memory tier of Mac mini

These are estimates to help you choose a machine, not benchmark results. The method: a 4-bit quantized model takes about 0.5 bytes per parameter; macOS lets the GPU use about 75% of memory; a further 20% is reserved for conversation context. Real-world figures vary with the model, context length and number of concurrent users — Namtech will test on real hardware for you before you commit to a configuration.

Mac mini M6 or M5 Pro: which one for local AI?

Choose M6 when you are just starting to trial local AI, running models under about 38B parameters for a handful of users. Choose M5 Pro when you need larger models (up to ~76B): it offers 24–64GB of memory and 307GB/s of memory bandwidth, versus 153GB/s – 170GB/s on M6.

M6M5 Pro
CPU / GPU12 / 12 cores15/18 / 16/20 cores
Neural EngineDual 16-core Neural Engine16 cores
Unified memory16–32GB24–64GB
Memory bandwidth153GB/s – 170GB/s307GB/s
Thunderbolt ports (back)3× Thunderbolt 4 (USB-C, up to 40Gb/s)3× Thunderbolt 5 (USB-C, up to 120Gb/s)
Storage256GB – 2TB512GB – 8TB
Max model (estimate, 4-bit)~38B~76B
Namtech price (VAT included)30.000.000₫ – 43.200.000₫57.600.000₫ – 97.200.000₫

Bandwidth determines how fast text is generated; GPU core count determines how quickly a long prompt is processed. Chip, RAM and bandwidth figures from apple.com/vn, checked September 24, 2026; bandwidth for the M5 Pro with 18-core CPU and 20-core GPU comes from Apple’s MacBook Pro spec page, as the Mac mini page does not list it separately.

When Mac mini is enough, and when you need Mac Studio

Mac mini is enough when

You are just starting to trial local AI, running models up to about 76B parameters, with only a handful of users, or mostly summarizing and drafting short documents. Mac mini offers 16–64GB of memory.

Move up to Mac Studio when

You need larger models, long context, many people asking at once, or several models on one machine. Mac Studio offers 36–256GB of memory (models up to ~307B).

The lowest-priced Mac Studio configuration is the Mac Studio M5 Max 18CPU 32GPU 36GB 512GB at 84.000.000₫, which runs models up to ~43B. Our advice is straightforward: if a Mac mini is already enough for your workload, Namtech will tell you before you spend money on a Mac Studio.

On-premise AI on Mac mini: your data never leaves the office

On-premise AI means the model runs on a machine located at your company. Questions, documents and answers all stay on your internal network — the foundation for an internal chatbot, a Q&A assistant over your document library, file summarization and drafting.

Unified memory

The CPU and GPU share a single pool of memory. The whole model loads onto the machine, with no need to split it up across several graphics cards.

Fits in the office

Height 5.0 cm · Width 12.7 cm · Depth 12.7 cm. Sits neatly on a desk, with no need for a server room or rack cabinet.

Low power draw

Maximum continuous power of 155W for the whole machine, per Apple’s specifications.

Your data stays in-house

The model runs locally and does not call any outside service. Suitable for HR records, contracts, customer data and internal documents.

Namtech sells genuine machines, issues VAT invoices, and can install and tune the software that runs your models (MLX, Ollama or LM Studio) to your requirements (quoted separately).

Specifications common to all configurations

PortsBack: 3× Thunderbolt 4 (M6, up to 40Gb/s) or 3× Thunderbolt 5 (M5 Pro, up to 120Gb/s) — USB-C, USB 4 up to 40Gb/s, DisplayPort · 1× HDMI (multichannel audio support) · 1× 2.5Gb Ethernet (RJ-45) — configurable to 10Gb Ethernet (Nbase-T) · Front: 2× USB-C (USB 3, up to 10Gb/s) + 3.5 mm headphone jack · Wi-Fi 7 (802.11be), Bluetooth 6, Thread — Apple N1 chip
Display supportUp to 3 external displays · M6: two 6K@60Hz displays + one 5K@60Hz display · M5 Pro: three 6K@60Hz displays · with up to two displays: one display up to 8K@60Hz
DimensionsHeight 5.0 cm · Width 12.7 cm · Depth 12.7 cm
Weight0.67 kg or 0.73 kg depending on chip (per Apple’s spec page)
Power100–240V AC, maximum continuous power 155W · operating temperature 10–35°C
In the boxMac mini and power cord (1.8 m). Display, keyboard and mouse sold separately.

Source: Apple’s official technical specifications, checked on September 24, 2026.

Frequently asked questions about Mac mini for local AI

Can Mac mini run local AI?

Yes, with small and mid-size models. The lowest-priced version (16GB, 30.000.000₫) runs models up to about 19B parameters; the 64GB version up to about 76B (estimate, 4-bit quantization). If you need larger models or many people asking at once, choose Mac Studio, which offers up to 256GB of memory.

How much RAM do you need to run an LLM locally on Mac mini?

It depends on the model size: 16GB up to ~19B, 24GB up to ~28B, 32GB up to ~38B, 48GB up to ~57B, 64GB up to ~76B parameters (estimates at 4-bit quantization). The method: macOS lets the GPU use about 75% of memory, 20% is reserved for context, and each parameter takes about 0.5 bytes.

Can Mac mini run a 70B model?

Yes, but only with the 64GB version, and it is close to the limit. The lowest-priced configuration that can run a 70B model is the Mac mini M5 Pro 15CPU 16GPU 64GB 512GB at 90.600.000₫ (VAT included), which holds models up to about 76B at 4-bit quantization, leaving little room for long context. To run 70B with lighter quantization or for many people at once, you need more memory than Mac mini’s 64GB maximum — Mac Studio comes with up to 256GB.

How much do the Mac mini M6 and M5 Pro cost?

At Namtech, Mac mini M6 is priced from 30.000.000₫ to 43.200.000₫, and M5 Pro from 57.600.000₫ to 97.200.000₫ with the default storage. Prices include VAT and come with a VAT invoice and advice on choosing a configuration for the AI models you need to run. SSD upgrades and 10Gb Ethernet cost extra; choose them on each machine’s detail page.

What is the difference between Mac mini M6 and M5 Pro?

M5 Pro has 307GB/s of memory bandwidth versus 153GB/s – 170GB/s on M6, a 16- or 20-core GPU versus 12-core, and 24–64GB of memory (models up to ~76B) versus 16–32GB (up to ~38B). On the back, M5 Pro has 3× Thunderbolt 5 (USB-C, up to 120Gb/s), while M6 has 3× Thunderbolt 4 (USB-C, up to 40Gb/s). M5 Pro storage goes up to 8TB, M6 up to 2TB.

Mac mini or Mac Studio: which should I choose for local AI?

Choose Mac mini when the models you need to run are under about 76B parameters and there are few users: 16–64GB memory, from 30.000.000₫. Choose Mac Studio when you need larger models or many people querying at once: 36–256GB memory (models up to ~307B), from 84.000.000₫. Prices include VAT.

Do I need the 10Gb Ethernet upgrade?

It is not required. Every Mac mini comes with a 2.5Gb Ethernet port; the 10Gb Ethernet option costs an extra 3.300.000₫ (VAT included) and must be selected when you order the machine. It is worth considering if the machine often copies large files over your internal network; for everyday text Q&A, the built-in port is usually enough.

Can I upgrade the RAM after purchase?

No. Mac mini memory is built into the chip, so you must choose the right amount when you order. That is why you should work out the size of the models you plan to run before settling on a configuration.

What is the maximum storage for Mac mini?

M6 can be configured from 256GB to 2TB; M5 Pro from 512GB to 8TB. Storage holds the operating system, model files and documents; if you plan to keep many models or a large document library, choose extra capacity when you order.

Can Mac mini run an internal chatbot?

Yes, at a small scale. Mac mini can run a Q&A assistant over your internal document library for a group of employees on the company network, with no data leaving. Namtech can install and tune the software that runs your models (MLX, Ollama or LM Studio) to your requirements, quoted separately based on the scope of work.

Do you issue VAT invoices?

Yes. Prices listed on this page include VAT, and Namtech issues full VAT invoices to businesses. Configurations with upgraded RAM, SSD or Ethernet are built to order; we confirm the delivery date when we receive your request.

Request a quote

Get a Mac mini quote within 1 business day

Tell us what you plan to use AI for and how many people will use it — Namtech will recommend a configuration that fits your needs, with no overselling.

We reply within 1 business day. No spam, and we never share your information.