Mac mini M6 32GB
Maximum-memory M6 Mac mini and a strong low-power home AI server, with 32GB still limiting the largest model classes.
Memory configurations
The chip profile is shared, but memory headroom, runnable models, and price are calculated per configuration.
Task Fit
Strong fit for chat workloads in the current planner.
Strong fit for code workloads in the current planner.
Strong fit for rag workloads in the current planner.
Strong fit for agent workloads in the current planner.
Strong fit for vision workloads in the current planner.
Usable for embedding, with tradeoffs around speed, memory, or runtime maturity.
Usable for voice, with tradeoffs around speed, memory, or runtime maturity.
Not a primary fit for image generation in the current hardware pool.
Not a primary fit for video generation in the current hardware pool.
Runtime Support
Specs
Cost and Ops
Execution evidence
Execution recipes for Mac mini M6 32GB
Recipes connect hardware, a model artifact, tools, settings, verification, and a reportable result.
No verified recipe is linked to this record yet.
Compatibility estimates remain available in the planner. A recipe appears here only after its exact stack and verification protocol are documented.
Models This Hardware Can Run
Estimated from default model artifacts, VRAM, unified memory, and recommended RAM.
Google · Q4_0
Google · Q4_0
Moonshot AI · Q4_K_M
Google · Q4_K_M
DeepSeek · BF16
Alibaba · Q4_K_M
DeepSeek · BF16
· FP16
· FP16
Best For
Maximum-memory M6 Mac mini and a strong low-power home AI server, with 32GB still limiting the largest model classes.
Source Confidence
Similar Hardware
Base M6 Mac mini for efficient always-on local AI. The 16GB memory pool is its primary model-fit limit.
Middle M6 Mac mini configuration with enough headroom for 14B-class assistants and modest local RAG workloads.
Mac mini M4 16GB profile for local AI model planning.