j33-jev
j33-jev by J33-AI is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text.
Pricing
No hosted price is listed. The weights are open: the cost is your own compute.
Specifications
- Provider
- J33-AI
- Parameters
- 272M
- Released
- Oct 2026
- Open weights
- Yes
- Question types
- Choice (one of N options), Score (ordered rubric), Yes / no
- Mechanism
- Decoder LM with a decision readout
- Backbone
- google/embeddinggemma-2
- Jev-compatible request
- Yes
- Runs on CPU
- Yes
- License
- apache-2.0
- Hugging Face
- J33-AI/j33-jev
Self-reported by the publisher
The model's own claims, often on its own sets or a self-run copy of a public suite. Not independently verified and never ranked alongside measured results.
- LocalLLaMA/typed-decisions (test, 2,000 decisions)Self-reportedECE 0.019
- 0.752
Compare j33-jev with…
FAQ
How much does j33-jev cost?
j33-jev has no hosted price listed; its weights are open, so the cost is the compute you run it on.
What questions can j33-jev answer?
j33-jev answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.
Is j33-jev well calibrated?
No calibration measurement for j33-jev is recorded yet.
Is j33-jev open weight, and can it run on a CPU?
Yes, j33-jev has open weights. It is small enough to run on a CPU.
Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.