@meta
  v: 1
  route: /gpu/m4-max-128
  generated: 2026-06-10T09:12:10.481Z

@intent
  purpose:    Show what AI models fit on the M4 Max 128.
  audience:   ai-engineer, self-hoster, homelab-buyer
  capability: inspect_specs, find_fitting_models, compare_to_other_gpus

@state
  slug: m4-max-128
  name: M4 Max 128
  vram_gb: 128
  bandwidth_gbs: 546
  fp16_tflops: 42
  budget_8k_gb: 102
  category: apple
  summary: 128GB unified. Runs 70B at FP16 or 120B at Q6. The MacBook for serious inference.
  top_fitting_models[5]: mixtral-8x22b, gpt-oss-120b, command-r-plus, qwen-2-5-72b, llama-3-3-70b

@actions
  - id: compare
    method: GET
    href: /gpu/dgx-spark
  - id: compare
    method: GET
    href: /gpu/gaudi-3
  - id: compare
    method: GET
    href: /gpu/m5-max-128
  - id: compare
    method: GET
    href: /gpu/h200
  - id: view_calculator
    method: GET
    href: /#calculator
  - id: view_math
    method: GET
    href: /the-math

@context
  > 128GB unified. Runs 70B at FP16 or 120B at Q6. The MacBook for serious inference.

@nav
  self:      /gpu/m4-max-128
  parents:   [/]
  peers:     [/gpu/dgx-spark, /gpu/gaudi-3, /gpu/m5-max-128, /gpu/h200]
  drilldown: /the-math