Specs at a glance
| CPU | Apple M4 / M4 Pro, 10-14 cores |
| GPU / NPU | 10-20 core integrated GPU + Neural Engine |
| RAM options | 16 / 24 / 32 / 48 / 64 GB unified memory |
| Storage | NVMe SSD 256 GB to 2 TB |
| Power draw | 4-65 W (M4), 5-140 W (M4 Pro), idle to maximum per Apple |
| Form factor | 127 × 127 × 50 mm |
| Local LLM capability | Up to 70B Q4 |
| Price point | €699-2200 |
Memory and bandwidth (power: Apple's power consumption page): Apple, Mac mini (2024) Tech Specs, read on 16 October 2026. Price and the rest are our own estimates.
Choosing between devices? The hardware buyer's guide compares them by budget, and Local LLM benchmarks has the published speeds, machine by machine.
Overview
The Mac mini with 24 GB of unified memory or more is a strong small machine for local LLMs, because its GPU reads the model from that fast memory. On llama.cpp's Apple Silicon scoreboard, a 7B model at Q4_0 writes 24.11 tokens per second on the M4 and 50.74 on the M4 Pro with the 20-core GPU. Llama 3.3 70B at 4-bit is a 43 GB file: it loads at 48 GB with little to spare, 64 GB leaves room for the context and the agent, and no published scoreboard gives its speed. Pair it with NanoClaw, whose agents run in Docker containers, or with an agent that talks to Ollama, such as ZeroClaw, to keep the model on the machine. Until October 2026 this line credited NanoClaw with Apple-native sandboxing and ZeroClaw with fully offline operation; neither project documents that. The downside is Linux: Asahi Linux is impressive but not yet production-grade. If your stack assumes Linux, the M4 Mac Mini is more friction than it's worth. If you're macOS-native or willing to run macOS as the host, it's the desk machine to beat.
Best for
- Local LLM inference on 13B-70B models
- ZeroClaw production setups
- NanoClaw, with its agent containers in Docker Desktop
- Anyone wanting Apple Silicon performance per watt
Not for
- Linux-only stacks (yes, Asahi Linux exists, but it's a project)
- True portability (still mains power, still desk-bound)
- Cost-sensitive deployments (Linux mini PC offers more RAM/€)
Compatible self-hosted agents
Listed as compatible with Mac Mini M4 / M4 Pro from each agent's requirements, not from a test (with the caveats from “Best for” / “Not for” above):
Where to buy
Manufacturer page: https://www.apple.com/mac-mini/. The Amazon link is an affiliate link: it costs you nothing and funds the site. Details on our disclosure page.
See also: all AI hardware · AI agents tracker · AI CVEs · edge AI hardware buyer's guide · scan your AI stack · our methodology.