An open Jev-style decision model by Andy Zhang: a LoRA adapter on Gemma 4 26B-A4B (also on Gemma 4 12B) that reads a state and returns a temperature-calibrated probability for every option of a yes/no, choice or score question in one forward pass.
Caliber Flex 1B by OnePass. Decision-only model, exactly 1,000,000,000 parameters.
Decides
choice, score, noul
choice, noul, score
Architecture
ajev
llm
Fine-tuned from
google/gemma-4-26b-a4b-it
qwen/qwen3.5-0.8b-base
License
apache-2.0
caliber-flex-non-commercial-1.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
49 ms
—
p95 latency
—
—
Evaluation suite
Sequential requests, the maker's own measurement
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
Questions
What is the difference between ajev and caliber-flex-1b?
ajev is from Andy Zhang and caliber-flex-1b from onepass. Both have open weights you can download and run. Both answer choice, score and noul questions. ajev is licensed apache-2.0; caliber-flex-1b, other.
Which is more accurate, ajev or caliber-flex-1b?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, ajev or caliber-flex-1b?
ajev: Free (open weights). caliber-flex-1b: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run ajev or caliber-flex-1b locally?
Yes, both: systemone pull andy-zhang/ajev and systemone pull onepass/caliber-flex-1b download the weights.
