@meta
  v: 1
  route: /gpu/m2-ultra-192
  generated: 2026-08-01T10:47:59.389Z

@intent
  purpose:    Show what AI models fit on the M2 Ultra 192.
  audience:   ai-engineer, self-hoster, homelab-buyer
  capability: inspect_specs, find_fitting_models, compare_to_other_gpus

@state
  slug: m2-ultra-192
  name: M2 Ultra 192
  vram_gb: 192
  bandwidth_gbs: 800
  fp16_tflops: 54
  budget_8k_gb: 154
  category: apple
  summary: 192GB unified. Runs 405B at Q3. The Mac Pro / Studio answer to multi-GPU rigs.
  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/b200
  - id: compare
    method: GET
    href: /gpu/mi300x
  - id: compare
    method: GET
    href: /gpu/h100-nvl-2x
  - id: compare
    method: GET
    href: /gpu/h200
  - id: view_calculator
    method: GET
    href: /#calculator
  - id: view_math
    method: GET
    href: /the-math

@context
  > 192GB unified. Runs 405B at Q3. The Mac Pro / Studio answer to multi-GPU rigs.

@nav
  self:      /gpu/m2-ultra-192
  parents:   [/]
  peers:     [/gpu/b200, /gpu/mi300x, /gpu/h100-nvl-2x, /gpu/h200]
  drilldown: /the-math