10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 643 ms

1. 1Qwen: Qwen3.5-Flashverified and signedpassport

   modelrecord

   • tool-calling

     Can call tools (function calling).

   • text+image+video->text

     Takes text, image, video; returns text.

   • structured-outputs

     Can return JSON matching a schema.

2. 2Qwen3.5-9B-DeepSeek-V4-Flashverified and signedpassport

   modelrecord2,863 downloads/month

   • image-text-to-text

     Task: image-text-to-text

3. 3Qwen3.5-122B-A10B-DFlashverified and signedpassport

   modelrecord33,476 downloads/month

   • text-generation

     Task: text-generation

4. 4Qwen: Qwen3 Coder Flashverified and signedpassport

   modelrecord

   • text->text

     Takes text; returns text.

5. 5Qwen: Qwen3.8 Omni Flashverified and signedpassport

   modelrecord

   • text+image+audio+video->text

     Takes text, image, audio, video; returns text.

6. 6qwen/qwen3-ttsverified and signedpassport

   modelrecord

   • qwen/qwen3-tts

     A unified Text-to-Speech demo featuring three powerful modes: Voice, Clone and Design

7. 7qwen/qwen3-235b-a22b-instruct-2507verified and signedpassport

   modelrecord

   • qwen/qwen3-235b-a22b-instruct-2507

     Updated Qwen3 model for instruction following

8. 8qwen/qwen3-7-plusverified and signedpassport

   modelrecord

   • qwen/qwen3-7-plus

     Qwen3.7-Plus is Alibaba's cost-effective multimodal model with vision-language understanding, a 1 million token context window, and strong agentic coding and tool use.