Launches
Independent JEV-35B brings one-pass decisions to open weights
Community reports 1 source
A
AutoTrust JEV-35B
Model Oct 13, 2026
An independent open-weight Qwen 3.5 fine-tune built to return typed decisions rather than chat responses.
Visit primary link
1 source attached
What happened lately
AutoTrust JEV-35B timeline
AutoTrust AI’s JEV-35B is an Apache-2.0 open-weight fine-tune of Qwen3.5-35B-A3B for bounded decisions. Its English Hugging Face card describes yes/no, score and multiple-choice outputs, including up to 256 options in one pass. The repository, created October 11, includes model checkpoints and serving code; it was observed on Hugging Face’s trending list on October 13. AutoTrust says this is independent of TypeSafe AI’s hosted Jev product. Its benchmark and latency figures are author-run results, not independent tests or evidence of performance in every deployment.