Jev Multimodal

A multimodal decision model on Workers AI that takes text, images, audio, or video in one request and returns schema-constrained probabilities, built on a 30B mixture-of-experts backbone with about 3B parameters active.

Liquid AI's first decision model, a hosted API that adds image input to the Choice, Score, and Noul shape. Liquid reports it matching or beating GPT-6.1 Sol on four of six tested applications at 19x to 200x lower cost.

The vision sibling: the same text-trained System 1 head on Qwen3.8-27B's image encoder, taking images zero-shot, ranked first of 20 vision decision models on the community Jev Decision Index 0.3.

Liquid AI's 3.12B decision model built on LFM2.5-VL: state plus typed questions in one forward pass with zero output tokens, 48.57 on Decision Index 0.2.1 and 8 ms per decision on an RTX 4090.

A Jev-style typed-decision baseline built on the frozen Qwen3.5-4B checkpoint that accepts a local image path directly, letting the vision-language model score declared options without generating text. Ships scoring modes, a WebGPU browser demo and benchmark results measured on an RTX 3090.

Chinese-language research project for multimodal social-risk moderation: a local Qwen3-VL-32B with language-side LoRA emits structured evidence JSON, and a fixed Jev policy turns that evidence into risk bands, with frozen test leaderboards and pure-Jev ablations.

Multimodal finite-choice decision interface and MuJoCo robotic-arm workbench: dual-camera images and state go to a self-hosted Qwen3.5-9B with a corrective head, which returns one typed next-skill choice without generating text.

Turns local text and vision models into Jev-style decision models by reading probabilities from prefill logits alone, with SGLang, Transformers, and Apple Silicon MLX backends.