Autotrust releases multimodal JEV models with fast vision capabilities

Autotrust has released two new multimodal models, JEV-27B-VL and JEV-9B, available on Hugging Face. JEV-27B-VL is designed for image-to-text tasks and can be integrated with libraries like Transformers, vLLM, and SGLang. The JEV-9B model, an evolution of the Qwen3.5-9B, incorporates a "System 1" fast decision-making layer alongside a "System 2" reasoning layer, enabling it to perform visual tasks such as robot arm manipulation and computer interface control with impressive speed and accuracy. AI

IMPACT These models demonstrate advancements in multimodal AI, particularly in fast visual decision-making, potentially accelerating applications in robotics and user interface automation.

RANK_REASON The cluster contains direct announcements of new multimodal models from a developer (Autotrust) with instructions and details on their capabilities, hosted on Hugging Face. [lever_c_demoted from frontier_release: ic=2 ai=1.0]

Read on Hugging Face Trending Models →

• autotrust/JEV-27B-VL
• Dockerdocker
• Hugging Face
• OpenAI
• SGLang
• Transformers
• vLLM
• AutoTrust
• autotrust/JEV-9B
• Google Colab
• Kaggle
• Qwen3.5:9b
• System 1

• model release
• product

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →