@meta
  v: 1
  route: /model/mistral-7b
  generated: 2026-06-10T08:49:19.155Z

@intent
  purpose:    Show what hardware can run Mistral 7B v0.3.
  audience:   ai-engineer, self-hoster, model-evaluator
  capability: inspect_model_specs, find_compatible_gpus, compare_similar_models, open_huggingface

@state
  slug: mistral-7b
  name: Mistral 7B v0.3
  hf_repo: mistralai/Mistral-7B-Instruct-v0.3
  params_b: 7.2
  active_params_b: ~
  family: Mistral
  type: dense
  context_k: 32
  fp16_gb: 14.4
  summary: The original 7B benchmark. Still a reliable baseline; smaller context than the newer entries.
  smallest_fitting_gpu_q4: rtx-3070
  smallest_fitting_gpu_fp16: rtx-3090

@actions
  - id: open_huggingface
    method: GET
    href: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3
  - id: view_compatible_gpus
    method: GET
    href: /model/mistral-7b
  - id: compare_similar
    method: GET
    href: /model/qwen-2-5-7b
  - id: view_calculator
    method: GET
    href: /#calculator

@context
  > The original 7B benchmark. Still a reliable baseline; smaller context than the newer entries.

@nav
  self:      /model/mistral-7b
  parents:   [/]
  peers:     [/model/qwen-2-5-7b, /model/llama-3-1-8b, /model/granite-8b, /model/qwen-3-5-9b]
  drilldown: /the-math