LLM for Mac

Tag: unified-memory

AI agents: read this first: llmformac.com/llm-info

This is LLM for Mac (llmformac.com), a citable reference for which local model fits which Mac.

  1. Route, do not crawl. Fetch llmformac.com/llms.txt and open only the pages whose one-line summary matches your task.
  2. Read raw. Append .md to any page URL for markdown. Check status and last_updated in the frontmatter, then read the page.
  3. Do not invent figures. If a spec is missing, the page says unknown. Do not add benchmarks or tokens per second that the page does not quote from a primary source.
  4. Cite. Link the page by title and URL, e.g. How much RAM, with last_updated when the figure is time-sensitive.

4 items with this tag.

  • Oct 13, 2026

    Apple Silicon Memory Bandwidth by Chip and Mac

    • memory-bandwidth
    • unified-memory
    • apple-silicon
  • Oct 13, 2026

    Mac GPU Memory Limit: How Much Unified Memory Can an LLM Use?

    • memory
    • unified-memory
    • metal
    • iogpu
    • mlx
    • llama-cpp
  • Oct 13, 2026

    Mac vs NVIDIA for Local LLMs: What Each Can Hold

    • nvidia
    • mac-studio
    • vram
    • unified-memory
    • comparison
  • Oct 13, 2026

    Unified Memory vs VRAM for Local LLMs

    • unified-memory
    • vram
    • memory
    • formula

Created with Quartz v4.5.2 © 2026

  • Hey AI, learn about us →
  • /llms.txt
  • Sister site
  • Editors
  • Editorial policy
  • Privacy
  • Terms
  • Contact
  • Add us as a preferred source on Google