Models

Qwen 3.5 2B

Alibaba · March 2026

Needs ~2.2 GB VRAM. Not WebLLM low-resource.

Qwen 3.5 2B runs in your browser, on your own device. The model downloads once and stays there; what you type is never sent to Alibaba or to us , and no API key is involved.

  • Modalities

  • Context window

    262,144 tokens, ≈ 197,000 words · about 790 pages

    the model's own limit — how much your device can hold depends on its memory

  • Runs on: Your device, in the browser
  • Size: 2B

Files you can attach

  • ImagesNot supported
  • DocumentsNot supported
  • Text and codeTXT, MD, CSV, TSV, RPT, LOG, PY, TS, TSX, JS, JSX, CS, GO, JAVA, KT, SWIFT, CPP, C, H, PHP, RB, SQL, SH, PS1, HTML, CSS, SCSS, JSON, YAML, YML, XML, INI

Features

  • StreamingSupported
  • Function callingNot supported
  • Structured outputsSupported
  • Fine-tuningNot supported

Where it comes from

Model cardAlibaba's card for Qwen 3.5 2B
WeightsThe build your browser downloads
RuntimeWebLLM

Ready to try it?

Log in

Runs on your device · No API key · Your chats stay in your browser