@meta
  v: 1
  route: /gpu/m5-pro-64
  generated: 2026-06-10T09:23:25.249Z

@intent
  purpose:    Show what AI models fit on the M5 Pro 64.
  audience:   ai-engineer, self-hoster, homelab-buyer
  capability: inspect_specs, find_fitting_models, compare_to_other_gpus

@state
  slug: m5-pro-64
  name: M5 Pro 64
  vram_gb: 64
  bandwidth_gbs: 307
  fp16_tflops: 45
  budget_8k_gb: 51.5
  category: apple
  summary: "64GB unified, 307 GB/s. Neural Accelerator in each GPU core. Comfortable 70B at Q4_K_M."
  top_fitting_models[5]: gpt-oss-120b, command-r-plus, qwen-2-5-72b, llama-3-3-70b, mixtral-8x7b

@actions
  - id: compare
    method: GET
    href: /gpu/m2-max-64
  - id: compare
    method: GET
    href: /gpu/m3-max-64
  - id: compare
    method: GET
    href: /gpu/m4-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, 307 GB/s. Neural Accelerator in each GPU core. Comfortable 70B at Q4_K_M.

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