UTC

Qwen3.6 27B

Alibaba (Qwen) · open weights · served by 31 providers · tool calling, reasoning, image input, video input, pdf input

alibaba/qwen3.6-27b

Weights
Open
Released
2026-04-22
Knowledge cutoff
Not stated
Context window
262K
Deprecation dates

When each platform deprecates Qwen3.6 27B, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.

  • wandbdeprecated 2026-10-05wandb/Qwen/Qwen3.6-27Bsuccessor: wandb/Qwen/Qwen3.8-27B
Every upcoming deprecation →
Hugging Face repository

Qwen/Qwen3.6-27B at commit 8f33b98937, last changed 2026-11-07

Licence
apache-2.0
Access
Open download
Library
transformers
Formats
.safetensors
  • No model signature file is published with the weights.

What the Hub's scanners report

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

The model at this commit, its 15 weight files with their SHA-256.

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
  • AbacusQwen/Qwen3.6-27B
  • ai&qwen/qwen3.6-27b
  • Ambientqwen/qwen3.6-27b
  • ChutesQwen/Qwen3.6-27B-TEE
  • Cortecsqwen3.6-27b
  • Deep InfraQwen/Qwen3.6-27B
  • EmpirioLabs AIqwen3-6-27b
  • Groqqwen/qwen3.6-27bdeprecated
  • Hugging FaceQwen/Qwen3.6-27B
  • InferXQwen3.6-27B-FP8
  • Kilo Gatewayqwen/qwen3.6-27b
  • DevPass (LLM Gateway)qwen3.6-27b
  • LLM Gatewaygreenference/qwen3.6-27b
  • Merge Gatewayqwen/qwen3.6-27b
  • NanoGPTTEE/qwen3.6-27b
  • NanoGPTqwen/qwen3.6-27b
  • NanoGPTqwen/qwen3.6-27b:thinking
  • Novita AIqwen/qwen3.6-27b
  • Ofoxbailian/qwen3.6-27b
  • Ofoxqwen/qwen3.6-27b
  • OpenRouterqwen/qwen3.6-27b
  • OVHcloud AI Endpointsqwen3.6-27b
  • Pendraqwen3.6:27b
  • Phalaqwen/qwen3.6-27b
7 more providers

QVAC (qwen3.6-27b), SiliconFlow (Qwen/Qwen3.6-27B), SiliconFlow (China) (Qwen/Qwen3.6-27B), STACKIT (Qwen/Qwen3.6-27B), Thinking Machines (Qwen/Qwen3.6-27B), Venice AI (qwen3-6-27b), Vercel AI Gateway (alibaba/qwen3.6-27b)

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.