{
  "id": "deepseek-r1-distill-qwen-32b",
  "name": "DeepSeek-R1-Distill-Qwen-32B",
  "developer": "DeepSeek",
  "exact_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
  "verified_at": "2026-09-27",
  "evidence_level": "source-verified",
  "access": {
    "label": "Direct download",
    "gated": false
  },
  "license": {
    "name": "MIT",
    "commercial_use": "MIT license permits commercial use subject to its terms.",
    "eu_note": "No explicit EU territorial restriction identified in the reviewed model repository."
  },
  "architecture": {
    "parameters": "33B reported on model hub",
    "type": "Dense Qwen-derived distilled reasoning model",
    "context": "131,072",
    "modalities": "Text → text"
  },
  "runtimes": [
    "Transformers",
    "vLLM",
    "Docker Model Runner",
    "llama.cpp via quantizations"
  ],
  "hardware_note": "Raw-weight estimate is similar to other 32–33B dense models; quantized local deployment is practical on larger consumer systems.",
  "primary_source": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
  "third_party_runtime_evidence": [],
  "reference_page": "https://openweightmodels.eu/model-deepseek-r1-distill-qwen-32b.html",
  "change_history": "https://openweightmodels.eu/change-deepseek-r1-distill-qwen-32b.json"
}