Supporting case
Kev9Bv2 open local decision model
What happened
The model card dates Kev-9B v 2 to September 30 and identifies an Apache 2.0 adapter/head on an Apache 2.0 Qwen base. It returns probabilities over supplied options rather than generating text. Serving code targets a single 24GB-class GPU. October 5 rereading confirms the v 2 checkpoint and intended use.
Only 8,192-token context is validated despite a longer serving ceiling. The publisher advises workload calibration and human review for consequential decisions; results are self-reported.
Dates and implementation stage
September 30 release per model card
