{
  "id": "qwen3-coder-30b-a3b",
  "name": "Qwen3-Coder-30B-A3B-Instruct",
  "developer": "Qwen / Alibaba",
  "exact_model_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
  "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": "30B total / ~3B active",
    "type": "Mixture-of-Experts coding model",
    "context": "256K",
    "modalities": "Text → text/code"
  },
  "runtimes": [
    "Transformers",
    "vLLM",
    "SGLang",
    "llama.cpp"
  ],
  "hardware_note": "Designed for agentic coding; memory depends strongly on quantization and KV-cache length.",
  "primary_source": "https://github.com/QwenLM/Qwen3-Coder",
  "third_party_runtime_evidence": [],
  "reference_page": "https://openweightmodels.eu/model-qwen3-coder-30b-a3b.html",
  "owm_view": "Qwen3-Coder-30B-A3B is one of the more strategically interesting coding checkpoints because it combines agentic coding specialization, a 256K native context and a relatively small active-parameter footprint. OWM sees it as a strong example of how open weights can move from “chatbot alternative” to infrastructure for developer agents.",
  "seo_reference_verified_at": "2026-09-27",
  "change_history": "https://openweightmodels.eu/change-qwen3-coder-30b-a3b.json"
}