@meta
  v: 1
  route: /gpu/rtx-4060
  generated: 2026-06-10T07:39:49.561Z

@intent
  purpose:    Show what AI models fit on the RTX 4060.
  audience:   ai-engineer, self-hoster, homelab-buyer
  capability: inspect_specs, find_fitting_models, compare_to_other_gpus

@state
  slug: rtx-4060
  name: RTX 4060
  vram_gb: 8
  bandwidth_gbs: 272
  fp16_tflops: 121
  budget_8k_gb: 5.1
  category: rtx-40
  summary: "8GB Ada. Modern silicon, weak VRAM. 7B at Q5 and call it done."
  top_fitting_models[5]: qwen-3-5-9b, gemma-2-9b, llama-3-1-8b, granite-8b, mistral-7b

@actions
  - id: compare
    method: GET
    href: /gpu/rtx-3070
  - id: compare
    method: GET
    href: /gpu/rtx-3080
  - id: compare
    method: GET
    href: /gpu/arc-b580
  - id: compare
    method: GET
    href: /gpu/rtx-3060
  - id: view_calculator
    method: GET
    href: /#calculator
  - id: view_math
    method: GET
    href: /the-math

@context
  > 8GB Ada. Modern silicon, weak VRAM. 7B at Q5 and call it done.

@nav
  self:      /gpu/rtx-4060
  parents:   [/]
  peers:     [/gpu/rtx-3070, /gpu/rtx-3080, /gpu/arc-b580, /gpu/rtx-3060]
  drilldown: /the-math