Apple

Mac mini (M6, 2026)

M6Released September 22, 2026Launch price $899 (Apple US price, 16GB / 256GB)

The cheapest way into a Mac and the first Mac mini with Apple's M6: 12 CPU cores, a 12-core GPU with AI accelerators in every core, and fast enough at 1080p to play Cyberpunk 2077 at its "For This Mac" preset in the mid-50s fps. The 16GB base model runs 7-8B language models comfortably (a 4-bit 7B model is about 3.5GB) and its memory bandwidth is 153GB/s; the 24GB and 32GB options raise that to 170GB/s and leave room for 14B-class models. For bigger models or more than 32GB, step up to the M5 Pro.

Buy now Mac mini 55days since update
Just updated: the next model is a long way off. Last updated August 25, 2026, Mac mini (M6 and M5 Pro); the last 4 updates came every 714 days on average.

Against the line-up

Geekbench 6 CPU Single-core · points

#1 of 3 · The Verge; † another publication
  1. 1Mac mini M64,708
  2. 2Mac mini M5 Pro4,294†
  3. 3Mac mini M43,838

Geekbench 6 CPU Multi-core · points

#3 of 4 · The Verge; † another publication
  1. 1Mac mini M5 Pro29,104†
  2. 2Mac mini M4 Pro22,661
  3. 3Mac mini M621,405
  4. 4Mac mini M414,838

Cyberpunk 2077 1080p For This Mac · fps

#1 of 1 · Tom's Guide
  1. 1Mac mini M657

Blender Benchmark samples/min

#2 of 4 · Blender Open Data
  1. 1Mac mini M5 Pro3,643
  2. 2Mac mini M62,656
  3. 3Mac mini M4 Pro2,570
  4. 4Mac mini M41,276

The whole Mac mini line-up side by side, with prices

Every benchmark

Quoted from the publications that ran them; we don't test hardware ourselves. Figures from different publications were run on different systems and scenes, so compare within a row's source.

Cyberpunk 2077

SettingResultSource
1080p Default Mac settings
one source
55fps Engadget, Sep 21, 2026
Mac mini M6, 24GB, 1TB review unit
Engadget: "an average of 55 fps in 1080p with the default Mac graphics settings"
1080p For This Mac
one source
57fps Tom's Guide, Sep 21, 2026
Mac mini M6, 24GB review unit

Local LLM (llama.cpp / Ollama)

SettingResultSource
Llama 2 7B Q4_0, Generation
one source
35.7tok/s llama.cpp community benchmarks (GitHub), Oct 19, 2026
Mac mini M6, 12-core GPU, 32GB (170GB/s), macOS 27.0.1
llama-bench tg128 (generating 128 tokens), all layers on the GPU. The 16GB base model has 153GB/s.
Llama 2 7B Q4_0, Prompt processing
one source
989tok/s llama.cpp community benchmarks (GitHub), Oct 19, 2026
Mac mini M6, 12-core GPU, 32GB (170GB/s), macOS 27.0.1
llama-bench pp512 (reading a 512-token prompt), all layers on the GPU.
Llama 2 7B Q8_0, Generation
one source
21tok/s llama.cpp community benchmarks (GitHub), Oct 19, 2026
Mac mini M6, 12-core GPU, 32GB (170GB/s), macOS 27.0.1
llama-bench tg128 (generating 128 tokens), all layers on the GPU.

Blender Benchmark

SettingResultSource
Standard run
one source
2,656samples/min Blender Open Data, Oct 19, 2026
Apple M6 (GPU - 12 cores), Metal, Blender 5.2.0
Median score over the three scenes, 17 submitted runs
CPU
one source
335samples/min Blender Open Data, Oct 19, 2026
Apple M6 CPU, Blender 5.2.0
Median score over the three scenes, 16 submitted runs.

Geekbench 6 CPU

SettingResultSource
Multi-core
one source
21,405points Tom's Guide, Sep 21, 2026
Mac mini M6, 24GB review unit
Geekbench 6.7
Single-core
one source
4,708points Tom's Guide, Sep 21, 2026
Mac mini M6, 24GB review unit
Geekbench 6.7

Sources

As an Amazon Associate we earn from qualifying purchases, and we may earn from other shop links. Amazon's price is on Amazon; Best Buy's is read from Best Buy and shown with the time it was checked.