ModelScope releases JEV-35B, a 35B decision model under Apache 2.0

AIAutoTrust Labs releases JEV-35B, which builds on Qwen3.5-35B-A3B and activates about 3B of its 35B parameters per token under an Apache 2.0 license. The model compares up to 256 text or image options in one pass, returns calibrated probabilities, and reaches around 204ms median single-request latency in its tested setup. An NVFP4 version is 25.6GB and keeps 96.6% of the BF16 model's decisions, enabling local deployment on a single 32–48GB GPU.

AIModelScope releases JEV-35B, a System 1 decision model built on Qwen3.5-35B-A3B that activates about 3B of its 35B parameters per token, under Apache 2.0. It compares up to 256 text or image options in one pass, returns calibrated probabilities, and reaches about 204ms median single-request latency in its tested setup. The NVFP4 version is 25.6GB and runs on a single 32–48GB GPU, preserving 96.6% of the BF16 model's decisions.