UTC

Qwen3.5 397B-A17B

Alibaba (Qwen) · open weights · served by 39 providers · tool calling, reasoning, image input, video input

alibaba/qwen3.5-397b-a17b

Weights
Open
Released
2026-02-15
Knowledge cutoff
2025-04
Context window
262K
Deprecation dates

When each platform deprecates Qwen3.5 397B-A17B, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.

  • Together AIdeprecated 2026-06-29together_ai/Qwen/Qwen3.5-397B-A17Bsuccessor: together_ai/Qwen/Qwen4-Max
Every upcoming deprecation →
Hugging Face repository

Qwen/Qwen3.5-397B-A17B at commit 8472618112, last changed 2026-04-24

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

43 weight files, 43 with a scan result. No scanner reports an issue with them.

The model at this commit, its 43 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
  • Adaptionqwen3.5-397b
  • AIHubMixqwen3.5-397b-a17b
  • ChutesQwen/Qwen3.5-397B-A17B-TEE
  • Cloudflare AI Gatewayalibaba/qwen3.5-397b-a17b
  • Cortecsqwen3.5-397b-a17b
  • Deep InfraQwen/Qwen3.5-397B-A17B
  • DigitalOceanqwen3.5-397b-a17b
  • EmpirioLabs AIqwen3-5-397b-a17bdeprecated
  • GreenPTqwen3.5-397b-a17b
  • Hugging FaceQwen/Qwen3.5-397B-A17B
  • InfomaniakQwen/Qwen3.5-397B-A17B-FP8beta
  • Jalapeno CloudQwen3.5-397B-A17B
  • Kilo Gatewayqwen/qwen3.5-397b-a17b
  • DevPass (LLM Gateway)qwen35-397b-a17b
  • LLM Gatewayalibaba/qwen35-397b-a17b
  • LLM Gatewaynovita/qwen35-397b-a17b
  • LLMTRqwen/qwen3.5-397b-a17b
  • Merge Gatewayqwen/qwen3.5-397b-a17b
  • Mixlayerqwen/qwen3.5-397b-a17b
  • NanoGPTqwen/qwen3.5-397b-a17b
  • NanoGPTqwen/qwen3.5-397b-a17b:thinking
  • Novita AIqwen/qwen3.5-397b-a17b
  • Ofoxbailian/qwen3.5-397b-a17b
  • Ofoxqwen/qwen3.5-397b-a17b
15 more providers

OpenRouter (qwen/qwen3.5-397b-a17b), OrcaRouter (qwen/qwen3.5-397b-a17b), OVHcloud AI Endpoints (qwen3.5-397b-a17b), Phala (qwen/qwen3.5-397b-a17b), Qiniu (qwen3.5-397b-a17b), Scaleway (qwen3.5-397b-a17b), SiliconFlow (Qwen/Qwen3.5-397B-A17B), SOKKAN Router (qwen/qwen3.5-397b-a17b), Thinking Machines (Qwen/Qwen3.5-397B-A17B), Thinking Machines (Qwen/Qwen3.5-397B-A17B:peft:262144), Together AI (Qwen/Qwen3.5-397B-A17B), TokenGo (qwen/qwen3.5-397b-a17b), UnoRouter (qwen3.5-397b-a17b:free), Venice AI (qwen3-5-397b-a17b), Watt Cloud (Qwen3.5-397B-A17B)

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.