{
  "id": "devstral-small-1-1",
  "name": "Devstral Small 1.1",
  "developer": "Mistral AI / All Hands AI",
  "exact_model_id": "mistralai/Devstral-Small-2507",
  "verified_at": "2026-09-27",
  "evidence_level": "source-verified",
  "access": {
    "label": "Direct download",
    "gated": false
  },
  "license": {
    "name": "Apache 2.0",
    "commercial_use": "Apache 2.0 allows commercial and non-commercial use.",
    "eu_note": "No explicit EU territorial restriction identified in the reviewed model materials."
  },
  "architecture": {
    "parameters": "24B",
    "type": "Dense coding model",
    "context": "128K",
    "modalities": "Text → text/code"
  },
  "runtimes": [
    "mistral-inference",
    "Transformers",
    "vLLM",
    "LM Studio",
    "llama.cpp"
  ],
  "hardware_note": "Publisher says it is light enough for a single RTX 4090 or a Mac with 32 GB RAM.",
  "primary_source": "https://huggingface.co/mistralai/Devstral-Small-2507",
  "third_party_runtime_evidence": [],
  "reference_page": "https://openweightmodels.eu/model-devstral-small-1-1.html",
  "change_history": "https://openweightmodels.eu/change-devstral-small-1-1.json"
}