@meta
  v: 1
  route: /gpu/h100
  generated: 2026-06-10T08:47:36.763Z

@intent
  purpose:    Show what AI models fit on the H100 80GB.
  audience:   ai-engineer, self-hoster, homelab-buyer
  capability: inspect_specs, find_fitting_models, compare_to_other_gpus

@state
  slug: h100
  name: H100 80GB
  vram_gb: 80
  bandwidth_gbs: 3350
  fp16_tflops: 989
  budget_8k_gb: 63
  category: datacenter
  summary: 80GB HBM3. The datacenter standard. Production-grade 70B at FP16 with long context.
  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/m3-max-96
  - id: compare
    method: GET
    href: /gpu/rtx-6000-pro
  - id: compare
    method: GET
    href: /gpu/m2-max-64
  - id: compare
    method: GET
    href: /gpu/m3-max-64
  - id: view_calculator
    method: GET
    href: /#calculator
  - id: view_math
    method: GET
    href: /the-math

@context
  > 80GB HBM3. The datacenter standard. Production-grade 70B at FP16 with long context.

@nav
  self:      /gpu/h100
  parents:   [/]
  peers:     [/gpu/m3-max-96, /gpu/rtx-6000-pro, /gpu/m2-max-64, /gpu/m3-max-64]
  drilldown: /the-math