See the speed before choosing hardware

Analysis of upcoming releasesUpdated September 2026

Mac mini M6 24GB Integrated memory 24GB · Usable space for model: approximately 20GB

M6 24GB configuration with 170GB/s memory bandwidth. You can compare the 12B class with some 27B Q4 models.

Hardware core specifications

available memory
20GB
Memory bandwidth
170GB/s
Estimated sustained LLM load
About 52W
Korean price range (KRW)
184 × KRW 10,000–235 × KRW 10,000

a person who fits well

  • Utilizes 20GB of available memory
  • Quiet finished product composition
  • Qwen3.6 35B-A3B (MoE) level local inference

In this case skip it

Actual sales configuration, runtime support, and actual performance may vary for pre-release products, so please check again at the time of purchase.

Recommended format for each device 4K input

The model you will experience with this equipment

MiniCPM5-2B

Required 2.07GB · spare time

MLX 4-bit

Decode

79.9 ~ 89 tok/s

First token

2.4 to 6.0 seconds

speed tuning

Qwen3.6 35B-A3B (MoE)

recommended

Required 21.28GB · tight

MLX 4-bit

Decode

17.3 ~ 26.9 tok/s

First token

4.5 ~ 11.7 s

speed tuning

Actual speed may vary depending on runtime version, cooling status, context length and quantization file.

On sales pages, look at memory before chips.

The model and speed assumptions above change if the product is not the 24GB configuration.

Frequently Asked Questions

What LLM can be run on the Mac mini M6 24GB?
You can compare MiniCPM5-2B, Qwen3.6 35B-A3B (MoE), etc. with 4K input and recommended formats. Memory requirements vary depending on model and context length.
What is the local LLM power of the Mac mini M6 24GB?
Expected to be around 52W under sustained load, with an actual range of 33–75W.
Are the displayed token speeds ground truth?
This is an estimated range calibrated to the calculator against official hardware specifications and verified benchmark ranges. Runtime, cooling, quantization may vary depending on file and context length.