@meta
  v: 1
  route: /gpu/m3-max-96
  generated: 2026-06-10T09:17:08.971Z

@intent
  purpose:    Show what AI models fit on the M3 Max 96.
  audience:   ai-engineer, self-hoster, homelab-buyer
  capability: inspect_specs, find_fitting_models, compare_to_other_gpus

@state
  slug: m3-max-96
  name: M3 Max 96
  vram_gb: 96
  bandwidth_gbs: 400
  fp16_tflops: 35
  budget_8k_gb: 76
  category: apple
  summary: "96GB unified. 70B at Q6 or 120B at Q4. Quiet, cool, portable."
  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/rtx-6000-pro
  - id: compare
    method: GET
    href: /gpu/h100
  - id: compare
    method: GET
    href: /gpu/dgx-spark
  - id: compare
    method: GET
    href: /gpu/gaudi-3
  - id: view_calculator
    method: GET
    href: /#calculator
  - id: view_math
    method: GET
    href: /the-math

@context
  > 96GB unified. 70B at Q6 or 120B at Q4. Quiet, cool, portable.

@nav
  self:      /gpu/m3-max-96
  parents:   [/]
  peers:     [/gpu/rtx-6000-pro, /gpu/h100, /gpu/dgx-spark, /gpu/gaudi-3]
  drilldown: /the-math