{
  "id": "smollm3-3b",
  "name": "SmolLM3-3B",
  "developer": "Hugging Face",
  "exact_model_id": "HuggingFaceTB/SmolLM3-3B",
  "verified_at": "2026-09-27",
  "evidence_level": "source-verified",
  "access": {
    "label": "Direct download",
    "gated": false
  },
  "license": {
    "name": "Apache 2.0",
    "commercial_use": "Commercial use permitted under Apache 2.0.",
    "eu_note": "No explicit EU territorial restriction identified in the reviewed license/materials."
  },
  "architecture": {
    "parameters": "3B",
    "type": "Compact decoder-only language model",
    "context": "64K trained / up to 128K with YaRN",
    "modalities": "Text → text"
  },
  "runtimes": [
    "Transformers",
    "llama.cpp via GGUF",
    "MLX community variants"
  ],
  "hardware_note": "3B scale makes local and edge-style experimentation substantially easier than 30B+ models.",
  "primary_source": "https://huggingface.co/HuggingFaceTB/SmolLM3-3B",
  "third_party_runtime_evidence": [],
  "reference_page": "https://openweightmodels.eu/model-smollm3-3b.html",
  "change_history": "https://openweightmodels.eu/change-smollm3-3b.json"
}