7B–9B in Q4, Whisper, and lightweight local tools.
Mac AI finder
Unified-Memory Workbench
Set model, quantization, and context, then see how much unified memory your workflow actually needs.
Quick check
Rules of thumb for Mac AI
13B models, coding checks, and longer prompts.
30B in Q4 and serious local development work.
70B+, very long context, and heavy multimodality.
Generation atlas
M1 through M5, without invented chips
The finder covers every released Apple silicon chip family from M1 through M5 and separates current from used options.
Workflow finder
Choose by task
The best Mac depends on more than the model: code, long documents, speech, and image workflows stress memory differently.
Pro 48 GB+ Coding assistant (70B class)
Large coding agents, repository context, and tool calls.
Balanced 24 GB+ Coding LLM (32B class)Local code models for patches, reviews, and CLI checks.
Context 24–48 GB Long documents (128K context)PDFs, source bundles, and long contexts without constant trimming.
Vision 16 GB+ Image analysisImage analysis, screenshots, OCR, and light multimodality.
Audio 8–16 GB Speech to text (Whisper)Local transcription, fast and without cloud upload.
Daily 16–24 GB All-round on the goMobile mix of chat, coding, research, and media.