Skip to content

ezjev 4B s2

everettjfDecision modelOpen weights

ezjev 4B s2 by everettjf is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 47.0 on the Jev Decision Index (rank 58).

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider
everettjf
Parameters
5B
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
Qwen/Qwen3.5-4B
Jev-compatible request
Yes
Runs on CPU
No
License
other
Hugging Face
everettjf/ezjev-4b-s2

Benchmarks

Jev Decision IndexECE 0.063
47.0

Jev Decision Index: public 50.8, ECE 0.063, Brier 0.403. Lower ECE means its probabilities can be taken at face value.

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.

Jev Decision Index public suite (self-run)Self-reportedDecision Index public balanced skill, edition 0.2.1 kit (release-v2.1), self-run
51.1

Speed & latency

Median latency per call (Decision Index)
36 ms

Compare ezjev 4B s2 with…

FAQ

How much does ezjev 4B s2 cost?

ezjev 4B s2 has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can ezjev 4B s2 answer?

ezjev 4B s2 answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is ezjev 4B s2 well calibrated?

On the Jev Decision Index its expected calibration error (ECE) is 0.063; below about 0.05, a stated 80% confidence is right roughly 80% of the time.

Is ezjev 4B s2 open weight, and can it run on a CPU?

Yes, ezjev 4B s2 has open weights. It needs a GPU to run at useful speed.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.