Qwen3.5: Towards Native Multimodal Agents (https://qwen.ai/blog?id=qwen3.5)

Alibaba’s Qwen just released the first two models in the Qwen 3.5 series - one open weights, one proprietary. Both are multi-modal for vision input.

The open weight one is a Mixture of Experts model called Qwen3.5-397B-A17B. Interesting to see Qwen call out serving efficiency as a benefit of that architecture:

Built on an innovative hybrid architecture that fuses linear attention (via Gated Delta Networks) with a sparse mixture-of-experts, the model attains remarkable inference efficiency: although it comprises 397 billion total parameters, just 17 billion are activated per forward pass, optimizing both speed and cost without sacrificing capability.

It’s 807GB on Hugging Face (https://huggingface.co/Qwen/Qwen3.5-397B-A17B), and Unsloth have a collection of smaller GGUFs (https://huggingface.co/unsloth/Qwen3.5-397B-A17B-GGUF) ranging in size from 94.2GB 1-bit to 462GB Q8_K_XL.

I got this pelican (https://simonwillison.net/tags/pelican-riding-a-bicycle/) from the OpenRouter hosted model (https://openrouter.ai/qwen/qwen3.5-397b-a17b) (transcript (https://gist.github.com/simonw/625546cf6b371f9c0040e64492943b82)):

The proprietary hosted model is called Qwen3.5 Plus 2026-02-15, and is a little confusing. Qwen researcher Junyang Lin says (https://twitter.com/JustinLin610/status/2023340126479569140):

Qwen3-Plus is a hosted API version of 397B. As the model natively supports 256K tokens, Qwen3.5-Plus supports 1M token context length. Additionally it supports search and code interpreter, which you can use on Qwen Chat with Auto mode.

Here’s its pelican (https://gist.github.com/simonw/9507dd47483f78dc1195117735273e20), which is similar in quality to the open weights model:

Tags: ai (https://simonwillison.net/tags/ai), generative-ai (https://simonwillison.net/tags/generative-ai), llms (https://simonwillison.net/tags/llms), vision-llms (https://simonwillison.net/tags/vision-llms), qwen (https://simonwillison.net/tags/qwen), pelican-riding-a-bicycle (https://simonwillison.net/tags/pelican-riding-a-bicycle), llm-release (https://simonwillison.net/tags/llm-release), openrouter (https://simonwillison.net/tags/openrouter), ai-in-china (https://simonwillison.net/tags/ai-in-china)