@meta
  v: 1
  route: /model
  generated: 2026-06-10T07:02:36.344Z

@intent
  purpose:    Browse every model in the curated catalog. Find a model that fits a card.
  audience:   ai-engineer, self-hoster, model-evaluator
  capability: list_all_models, compare_by_params, open_huggingface, drill_into_model

@state
  total: 30
  families[11]{family,count}:
    Meta,5
    Alibaba,8
    OpenAI,2
    Mistral,4
    Microsoft,2
    Google,3
    DeepSeek,2
    01.AI,1
    Cohere,1
    IBM,1
    BigCode,1
  params_min_b: 1.23
  params_max_b: 671
  moe_count: 9
  slugs[30]: llama-3-2-1b, llama-3-2-3b, llama-3-1-8b, llama-3-3-70b, llama-3-1-405b, qwen-2-5-7b, qwen-2-5-32b, qwen-2-5-coder-32b, qwen-2-5-72b, qwen-3-30b-a3b, qwen-3-5-9b, qwen-3-6-27b, qwen-3-6-35b-a3b, gpt-oss-20b, gpt-oss-120b, mistral-7b, mistral-small-3, mixtral-8x7b, mixtral-8x22b, phi-4-mini, phi-4, gemma-2-9b, gemma-4-e4b, gemma-4-26b, deepseek-v3, deepseek-r1, yi-34b, command-r-plus, granite-8b, starcoder2-15b

@actions
  - id: view_calculator
    method: GET
    href: /#calculator
  - id: view_math
    method: GET
    href: /the-math
  - id: browse_gpus
    method: GET
    href: /gpu/

@context
  > Index of all curated open-weight models. 20 entries across Meta, Alibaba, Mistral, Microsoft, Google, DeepSeek, Cohere, IBM, BigCode, 01.AI. Each card links to a detail page with the GPU recommendation matrix across FP16 / Q8_0 / Q6_K / Q5_K_M / Q4_K_M quants, and a Hugging Face link.

@nav
  self:      /model/
  parents:   [/]
  peers:     [/gpu/]
  drilldown: /model/llama-3-1-70b