10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 678 ms

1. 1Qwen2.5-VL-OFT-LIBERO-4in1verified and signedpassport

   modelrecord174 downloads/month

   • robotics

     Task: robotics

2. 2Qwen2.5-Omni-7B-AWQverified and signedpassport

   modelrecord13,830 downloads/month

   • any-to-any

     Task: any-to-any

3. 3Qwen2.5-VL-72B-Instructverified and signedpassport

   modelrecord66,671 downloads/month

   • image-text-to-text

     Task: image-text-to-text

4. 4lucataco/qwen2-vl-7b-instructverified and signedpassport

   modelrecord

   • lucataco/qwen2-vl-7b-instruct

     Latest model in the Qwen family for chatting with video and image models

5. 5Qwen2.5-VL-7B-Instruct-NVFP4verified and signedpassport

   modelrecord1,665,246 downloads/month

   • text-generation

     Task: text-generation

6. 6aodianyun/qwen2-vl-7bverified and signedpassport

   modelrecord

   • aodianyun/qwen2-vl-7b

7. 7qwen2.5verified and signedpassport

   APIbentoml/openllm-modelsrecord68 stars

   • qwen2.5__generate

8. 8fine-tuning-openvla-oftverified and signedpassport

   skillorchestra-research/ai-research-skillsrecord

   • fine-tuning-openvla-oft

     Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or di

9. 9Qwen: Qwen2.5 VL 72B Instructverified and signedpassport

   modelrecord

   • structured-outputs

     Can return JSON matching a schema.

10. 10Qwen2.5-VL 32B GGUF Chatdemo or tutorialno passport yet

    MCP serverrecord

    • qwen2_5_vl_32b_gguf_clear_chat