@meta
  v: 1
  route: /gpu/h200
  generated: 2026-06-10T08:47:35.074Z

@intent
  purpose:    Show what AI models fit on the H200.
  audience:   ai-engineer, self-hoster, homelab-buyer
  capability: inspect_specs, find_fitting_models, compare_to_other_gpus

@state
  slug: h200
  name: H200
  vram_gb: 141
  bandwidth_gbs: 4800
  fp16_tflops: 989
  budget_8k_gb: 113
  category: datacenter
  summary: "141GB HBM3e. H100 with more memory. 70B at FP16 with extreme context, or 120B at Q8."
  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/m4-max-128
  - id: compare
    method: GET
    href: /gpu/m5-max-128
  - id: view_calculator
    method: GET
    href: /#calculator
  - id: view_math
    method: GET
    href: /the-math

@context
  > 141GB HBM3e. H100 with more memory. 70B at FP16 with extreme context, or 120B at Q8.

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