@meta
  v: 1
  route: /gpu/m3-max-64
  generated: 2026-06-10T09:11:15.628Z

@intent
  purpose:    Show what AI models fit on the M3 Max 64.
  audience:   ai-engineer, self-hoster, homelab-buyer
  capability: inspect_specs, find_fitting_models, compare_to_other_gpus

@state
  slug: m3-max-64
  name: M3 Max 64
  vram_gb: 64
  bandwidth_gbs: 400
  fp16_tflops: 35
  budget_8k_gb: 50
  category: apple
  summary: 64GB unified. Comfortable 70B at Q4_K_M with the whole machine to itself.
  top_fitting_models[5]: command-r-plus, qwen-2-5-72b, llama-3-3-70b, mixtral-8x7b, qwen-3-6-35b-a3b

@actions
  - id: compare
    method: GET
    href: /gpu/m2-max-64
  - id: compare
    method: GET
    href: /gpu/m4-pro-64
  - id: compare
    method: GET
    href: /gpu/m5-pro-64
  - id: compare
    method: GET
    href: /gpu/h100
  - id: view_calculator
    method: GET
    href: /#calculator
  - id: view_math
    method: GET
    href: /the-math

@context
  > 64GB unified. Comfortable 70B at Q4_K_M with the whole machine to itself.

@nav
  self:      /gpu/m3-max-64
  parents:   [/]
  peers:     [/gpu/m2-max-64, /gpu/m4-pro-64, /gpu/m5-pro-64, /gpu/h100]
  drilldown: /the-math