Apple SiliconApple

Apple Mac mini M4 24GB

Name: Apple Mac mini M4 24GB
Brand: Apple
SKU: mac-mini-m4-24gb

Curated Aggregate·2024-11-224 workloads · 4 records

MyAI RatingNot scoredInsufficient comparison evidence

VRAM

24 GB

TDP

22 W

MSRP

$999

Perf/W

0.77 tok/s/W

Cost/1K tok

$0.62/M

Tested

2024-11-22

Quick answer

How fast is Apple Mac mini M4 24GB for local AI workloads?

Apple Mac mini M4 24GB has a source-attributed result of 52.0 tok/s on Phi-3 Mini (batch 1, 4096-token context, Q4_K_M; runtime not documented). This is a reference report, not an independently verified lab result. A 70B Q4_K_M artifact needs roughly 40GB for weights alone; smaller memory configurations require explicit offload or model splitting and do not establish full-GPU residency.

Verdict

Apple Mac mini M4 24GB with 24GB VRAM at 22W TDP, scored across 4 workloads with 4 benchmark records.

Reference workload

Phi-3 Mini

52 tok/s

Quantization

Q4_K_M

4K context · batch 1

LLM Inference Performance

Benchmarks (4 workloads)

Workload	Score	Quant	Context	σ	Status	Tested
Llama 3 8B Q4 llm	17.0tok/s	Q4_K_M	8K	,	Curated Aggregate	2024-11-22
Gemma 2 9B llm	14.0tok/s	Q4_K_M	4K	,	Curated Aggregate	2024-12-01
Mistral 7B llm	23.0tok/s	Q4_K_M	4K	,	Curated Aggregate	2024-12-18
Phi-3 Mini llm	52.0tok/s	Q4_K_M	4K	,	Curated Aggregate	2025-01-04

MyAI Score: not scored

There is insufficient comparable evidence to score Apple Mac mini M4 24GB. A score needs results for multiple devices with matching workload, runtime version, quantization, context and batch size.

Workload Fit

Planning estimates for 24GB: weights plus at least 2GB or 10% overhead. Actual KV cache depends on model, context and cache format; confirm the artifact before buying.

FP16

7-8B

Excellent

13-14B

Excellent

Won't fit

32B

Good

Won't fit

70B

Won't fit

Reported batch-one examples

Phi-3 Mini52 tok/s

Mistral 7B23 tok/s

Gemma 2 9B14 tok/s

Source

Phi-3 on M4 24GB.

View source How we benchmark →

Public Trust Layer

Trust score

6/10

MyAI rating

Not scored

Runs

Not documented

Freshness

Stale

Source-linked row with explicit verification status.

Record date: 2025-01-04; 613 days old.

Open primary source

Best place to start

Where to buy

Search first

Retailer we'd check first

Amazon search

Amazon is a fast way to check live availability, but memory tier and exact SKU matter more than the first visible price.

Search Amazon listings

+Cross-check the current ask against $999 and any reputable open-box or used options.
+Verify RAM, storage, and chip binning carefully. Small spec differences change AI usability dramatically.
+If you plan long 24/7 inference runs, warranty and thermals matter more than a tiny discount.

There is insufficient comparable evidence for a purchase recommendation. Check model fit, software support and a current seller quote.

Affiliate note: we do not have a device-level ASIN yet, so this opens tagged Amazon search results for the exact product name.