UTC

Qwen3.5 35B-A3B

Alibaba (Qwen) · open weights · served by 25 providers · tool calling, reasoning, image input, video input

alibaba/qwen3.5-35b-a3b

Weights
Open
Released
2026-02-23
Knowledge cutoff
2025-04
Context window
262K
Deprecation dates

When each platform deprecates Qwen3.5 35B-A3B, 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/Qwen3.5-35B-A3Bsuccessor: wandb/Qwen/Qwen3.6-35B-A3B
Every upcoming deprecation →
Hugging Face repository

Qwen/Qwen3.5-35B-A3B at commit 59d61f3ce6, last changed 2026-04-24

Licence
apache-2.0
Access
Open download
Library
transformers
Formats
.safetensors

What the Hub's scanners report

14 weight files, 14 with a scan result. No scanner reports an issue with them.

The model at this commit, its 14 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.AIqwen3.5-35b-a3b
  • AIHubMixqwen3.5-35b-a3b
  • Deep InfraQwen/Qwen3.5-35B-A3B
  • DoublewordQwen/Qwen3.5-35B-A3B-FP8-dottxt
  • EmpirioLabs AIqwen3-5-35b-a3b
  • Hugging FaceQwen/Qwen3.5-35B-A3B
  • Jalapeno CloudQwen3.5-35B-A3B
  • Kilo Gatewayqwen/qwen3.5-35b-a3b
  • DevPass (LLM Gateway)qwen3.5-35b-a3b
  • LLM Gatewayalibaba/qwen3.5-35b-a3b
  • Merge Gatewayqwen/qwen3.5-35b-a3b
  • Mixlayerqwen/qwen3.5-35b-a3b
  • NanoGPTqwen/qwen3.5-35b-a3b
  • NanoGPTqwen/qwen3.5-35b-a3b:thinking
  • Novita AIqwen/qwen3.5-35b-a3b
  • Ofoxbailian/qwen3.5-35b-a3b
  • Ofoxqwen/qwen3.5-35b-a3b
  • OpenRouterqwen/qwen3.5-35b-a3b
  • OrcaRouterqwen/qwen3.5-35b-a3b
  • Requestyqwen3.5-35b-a3b
  • SiliconFlowQwen/Qwen3.5-35B-A3B
  • SiliconFlow (China)Qwen/Qwen3.5-35B-A3B
  • stepping stone AGQwen/Qwen3.5-35B-A3B-FP8
  • Venice AIqwen3-5-35b-a3b
1 more providers

Watt Cloud (Qwen3.5-35B-A3B)

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.