UTC

Qwen3 30B A3B

Alibaba (Qwen) · open weights · served by 15 providers · tool calling, reasoning

alibaba/qwen3-30b-a3b

Weights
Open
Released
2025-04-28
Knowledge cutoff
2025-04
Context window
131K
Hugging Face repository

Qwen/Qwen3-30B-A3B at commit ad44e777bc, last changed 2025-07-26

Licence
apache-2.0
Access
Open download
Library
transformers
Formats
.safetensors
  • No model signature file is published with the weights.
  • Built on Qwen/Qwen3-30B-A3B-Base.

What the Hub's scanners report

16 weight files, 15 with a scan result. No scanner reports an issue with them.

The model at this commit, its 16 weight files with their SHA-256 and its base models.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • 302.AIqwen3-30b-a3b
  • Cloudflare Workers AI@cf/qwen/qwen3-30b-a3b-fp8deprecated
  • Deep InfraQwen/Qwen3-30B-A3B
  • Heliconeqwen3-30b-a3b
  • Hugging FaceQwen/Qwen3-30B-A3B
  • Jiekou.AIqwen/qwen3-30b-a3b-fp8
  • Kilo Gatewayqwen/qwen3-30b-a3b
  • DevPass (LLM Gateway)qwen3-30b-a3b
  • LLM Gatewaygreenference/qwen3-30b-a3b
  • Merge Gatewayqwen/qwen3-30b-a3b
  • NanoGPTqwen/qwen3-30b-a3b
  • OpenRouterqwen/qwen3-30b-a3b
  • Qiniuqwen3-30b-a3bdeprecated
  • Vercel AI Gatewayalibaba/qwen-3-30b
  • ZeroGPUqwen3-30b-a3b-fp8
Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.