@meta
  v: 1
  route: /gpu/rtx-6000-ada
  generated: 2026-06-10T09:20:49.801Z

@intent
  purpose:    Show what AI models fit on the RTX 6000 Ada.
  audience:   ai-engineer, self-hoster, homelab-buyer
  capability: inspect_specs, find_fitting_models, compare_to_other_gpus

@state
  slug: rtx-6000-ada
  name: RTX 6000 Ada
  vram_gb: 48
  bandwidth_gbs: 960
  fp16_tflops: 364
  budget_8k_gb: 37
  category: workstation
  summary: "Same 48GB, modern silicon. Faster than A6000 across the board."
  top_fitting_models[5]: qwen-2-5-72b, llama-3-3-70b, mixtral-8x7b, qwen-3-6-35b-a3b, yi-34b

@actions
  - id: compare
    method: GET
    href: /gpu/a6000
  - id: compare
    method: GET
    href: /gpu/l40s
  - id: compare
    method: GET
    href: /gpu/w7900
  - id: compare
    method: GET
    href: /gpu/m2-max-64
  - id: view_calculator
    method: GET
    href: /#calculator
  - id: view_math
    method: GET
    href: /the-math

@context
  > Same 48GB, modern silicon. Faster than A6000 across the board.

@nav
  self:      /gpu/rtx-6000-ada
  parents:   [/]
  peers:     [/gpu/a6000, /gpu/l40s, /gpu/w7900, /gpu/m2-max-64]
  drilldown: /the-math