Skip to content

Yi-VL-34B

An open multimodal model for image dialogue

Visit official site

What yi-vl-34b is

The model is the open-source version of the Yi Visual Language series. It handles image understanding and recognition and carries multi-turn conversations about an image.

What you can do with it

  • Ask several questions about one image
  • Use bilingual text in a conversation
  • Work with fine-grained image detail

Key features

  • Multi-turn text and image dialogue
  • Bilingual text support
  • Fine-grained image resolution

Pros & cons

✓ What we like

  • Multi-turn text and image dialogue is listed
  • The material reports first place on MMM and CMMMU benchmarks

! What to watch out for

  • The material centers on the open-source Yi-VL release
  • Bilingual text and fine-grained resolution are the listed features

FAQ

What kind of model is it?

An open-source multimodal vision-language model.

Which benchmarks are named?

MMM and CMMMU.

Last reviewed: 2026-11-15

More LLM API platform tools

View all →

How we review