Apple

Mac mini (M4 Pro, 2024)

Name: Mac mini (M4 Pro, 2024)
Brand: Apple

Previous generationM4Released November 8, 2024Launch price $1,399 (launch price, 12-core CPU, 16-core GPU, 24GB / 512GB)

Best Buy · M4 Pro 12-core CPU, 16-core GPU, 24GB, 512GB Check price at Best Buy Amazon · M4 Pro 12-core CPU, 16-core GPU, 24GB, 512GB Check price on Amazon

Geekbench 6 CPU Multi-core22,661points#2 of 4 Blender Benchmark 2,570samples/min#3 of 4

The 2024 pro Mac mini, replaced by the M5 Pro model in September 2026 and still sold new while stock lasts. 273GB/s of memory bandwidth and up to 64GB still make it a capable local-AI box, but the M5 Pro generates text faster and reads prompts several times faster, so buy it only well below the new model's price.

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 Multi-core · points

#2 of 4 · The Verge; † another publication

1Mac mini M5 Pro29,104†
2Mac mini M4 Pro22,661
3Mac mini M621,405
4Mac mini M414,838

Blender Benchmark samples/min

#3 of 4 · Blender Open Data

1Mac mini M5 Pro3,643
2Mac mini M62,656
3Mac mini M4 Pro2,570
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.

Local LLM (llama.cpp / Ollama)

Setting	Result	Source
Llama 2 7B Q4_0, Generation one source	49.6tok/s	llama.cpp community benchmarks (GitHub), Oct 19, 2026 M4 Pro, 16-core GPU, 273GB/s llama-bench tg128 (generating 128 tokens), all layers on the GPU.
Llama 2 7B Q4_0, Prompt processing one source	364tok/s	llama.cpp community benchmarks (GitHub), Oct 19, 2026 M4 Pro, 16-core GPU, 273GB/s llama-bench pp512 (reading a 512-token prompt), all layers on the GPU.
Llama 2 7B Q8_0, Generation one source	30.5tok/s	llama.cpp community benchmarks (GitHub), Oct 19, 2026 M4 Pro, 16-core GPU, 273GB/s llama-bench tg128 (generating 128 tokens), all layers on the GPU.

Blender Benchmark

Setting	Result	Source
Standard run one source	2,570samples/min	Blender Open Data, Oct 19, 2026 Apple M4 Pro (GPU - 16 cores), Metal, Blender 5.2.0 Median score over the three scenes, 11 submitted runs
CPU one source	362samples/min	Blender Open Data, Oct 19, 2026 Apple M4 Pro CPU, Blender 5.2.0 Median score over the three scenes, 32 submitted runs. Blender Open Data does not split the 12- and 14-core CPUs.

Geekbench 6 CPU

Setting	Result	Source
Multi-core one source	22,661points	Tom's Guide, Sep 21, 2026 Mac mini M4 Pro (configuration not stated) Geekbench 6.7, in the Mac mini M6 review

Specs

Chip	Apple M4 Pro
CPU cores	12 (8 performance, 4 efficiency); 14 optional
GPU cores	16
Neural Engine	38 TOPS
Memory (base)	24 GB
Memory (max)	64 GB
Memory bandwidth	273 GB/s
Storage (base)	512 GB
Storage (max)	8 TB
Ports	3x Thunderbolt 5, HDMI, Gigabit Ethernet (10Gb option), 2x USB-C 10Gb/s and headphone jack on the front
External displays	Up to 3
Max power	155 W

From Apple Support: Mac mini (2024) tech specs (2026-10-19), Apple Newsroom: the new Mac mini (2024) (2024-10-29), Apple Newsroom: Apple introduces M4 Pro and M4 Max (Neural Engine) (2024-10-30).

Compare it

Sources

Blender Open Data (results database)
Tom's Guide (review)
llama.cpp community benchmarks (GitHub) (results database)

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.