Mac mini M4 Pro 24GB Integrated memory 24GB · Usable space for model: approximately 20GB
This configuration prioritizes the creation speed of the 12B model with high bandwidth within the 24GB loading limit.
Speed and memory for the same model
Hardware core specifications
- Available memory
- 20GB
- Memory bandwidth
- 273GB/s
- Estimated sustained LLM load
- About 86W
- Korean price range (KRW)
- 200 × KRW 10,000–330 × KRW 10,000
Who it fits
- Utilizes 20GB of available memory
- Quiet finished product composition
- K2 Horizon MoVA 36B-A4B-level local inference
Skip it if
Since the operating system and KV cache use the same memory, headroom quickly decreases for long contexts or models above 20B.
Recommended format for each device 4K input
The model you will experience with this equipment
K2 Horizon 0.9B
Required 1.03GB · spare time
MLX 4-bit
Decode
370.9 ~ 412.1 tok/s
First token
0.76 to 1.7 seconds
K2 Horizon MoVA 36B-A4B
recommendedRequired 21.94GB · tight
MLX 4-bit
Decode
20.8 ~ 32.4 tok/s
First token
4.8 to 10.5 seconds
Actual speed varies with runtime version, cooling, 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 M4 Pro 24GB?
- K2 Horizon 0.9B, K2 Horizon MoVA 36B-A4B and others with a 4K input and the recommended format. Required memory varies by model and context length.
- What is the local LLM computing power of the Mac mini M4 Pro 24GB?
- Sustained load is about 86 W, with an actual range of 58–115 W.
- Are the displayed token speeds ground truth?
- This is a range aligned to collected benchmark measurements under the same conditions. Combinations without a matching measurement are estimated from the nearest result and vary with runtime, cooling, quantization file and context length.
Equipment to compare together
similar memory
Mac mini M4 24GB
If you summarize short documents and ask about small sections of code, first check whether the model you plan to use gives useful answers. If a 12B Q4 model does the job, 32GB is worth considering only when your work needs more memory headroom.
similar memory
RTX 3090 24GB
If you own an RTX 3090, first check whether the target model and context fit in 24GB. Newer hardware alone is not a reason to replace a card that completes your work. For a used purchase, include power, cooling, case compatibility and return terms in the cost.
similar memory
RTX 4090 24GB
This is the machine to look at if you want to quickly process LLM and image creation that fit in 24GB and avoid the new high price.