Local AI Stats.
Skip to content

COMPUTER RECORD · SOURCED SPECIFICATIONS

Apple Mac mini M6 · 24GB: specifications and local LLMs

24 GB unified memory and 170 GB/s rated memory bandwidth. Compact and quiet; 170GB/s unified memory; strong Apple-silicon local-AI ecosystem; Wi-Fi 7 and 2.5GbE.

Catalog reviewed . Listing evidence: 2026-10-02. Price and performance records retain their own dates.

As an Amazon Associate I earn from qualifying purchases.

CPU, GPU, memory and storage

CPU
Apple M6 · 12-core · 12 cores / 12 threads
GPU
Apple M6 GPU · 12-core
Installed memory
24 GB · Unified · 170 GB/s · Amazon.com ASIN listing
Unified memory, not separate VRAM
24 GB shared with CPU and operating system
Memory bandwidth
170 GB/s rated / theoretical · Apple-published memory bandwidth for the 24GB M6 configuration.
Storage
512 GB · Amazon.com ASIN listing
Operating system
macOS 27 (manufacturer)
Expansion
Three Thunderbolt 4 ports; two front USB-C ports; HDMI 2.1; 2.5GbE; Wi-Fi 7

Fixed 24GB memory and internal storage limit model size; no CUDA support; no verified live Amazon price.

Amazon's variant map identifies this exact ASIN as M6 with 24GB unified memory and 512GB storage, without AppleCare+. Local-model fit depends on quantization, context and runtime overhead.

Amazon's direct Mac mini product-family page maps ASIN B0HGGHNG94 to M6, 24GB unified memory and 512GB SSD without AppleCare+. Apple technical and store pages match the CPU, GPU, memory and storage configuration. Current seller, stock and checkout price can change.

What local models could Mac mini M6 · 24GB run?

The 24 GB unified-memory pool gives a 16.8 GB initial weight budget using our 30% (minimum 2 GB) reserve. The CPU, GPU and OS share this capacity; software allocation limits still apply.

95 catalog files pass this size check. The largest is Qwen3.5-27B at 16.741 GB (Q4_K_M). This is a catalog weight limit, not a measured maximum practical model size. Context length, runtime and architecture support can rule out a candidate.

Model snapshot: 14 October 2026. The examples below use MMLU-Pro; models without that score are not ranked in this table.

MMLU-Pro memory candidates · GB = 1 billion bytes. Published scores may use different settings or precision.
Model / quantizationWeightsParametersScore / 100Score / GBBudget leftSources
Qwen3.5-4BQ4_K_M · Pareto choice2.741 GB4.206B79.128.85914.059 GBGet weights
Score source
MiniCPM5 2BQ4_K_M · Pareto choice1.561 GB2.517B70.845.34615.239 GBGet weights
Score source
Qwen3.5-9BQ4_K_M · Pareto choice5.681 GB9.653B82.514.52311.119 GBGet weights
Score source
LFM2.5 230MQ4_K_M · Pareto choice0.153 GB0.23B20.25132.00216.647 GBGet weights
Score source
Qwen3.5-27BQ4_K_M · Pareto choice16.741 GB27.781B86.15.1430.059 GBGet weights
Score source

Choose this computer in the memory tool · Compare its memory tier

Published LLM performance

Local AI Stats has not tested this computer. No matching token-speed result is recorded for this configuration.

Advertised compute peaks and bandwidth are not tokens per second. Compare the same model, quantization, context and concurrency.

Price and value

ASIN: B0HGGHNG94 · Amazon.com listing

No matching current USD price verified. No verified live Amazon.com price for this exact 24GB / 512GB configuration.

As an Amazon Associate I earn from qualifying purchases. Check the exact configuration, seller, marketplace and current price before buying.

GET NOW · Amazon

Related hardware

Compare all hardware · Compare budgets

Specification and price sources