Caliber Flex 1B by OnePass. Decision-only model, exactly 1,000,000,000 parameters.
Unofficial NoulXP package of Convai Innovations' Laya multilingual (Apache-2.0), fp32-o23: checked against the model's own answers, none changed. Not made by Convai Innovations.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
llm
laya
Fine-tuned from
qwen/qwen3.5-0.8b-base
convai-innovations/laya
License
caliber-flex-non-commercial-1.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
44.9 ms
p95 latency
—
742 ms
Evaluation suite
—
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 caliber-flex-1b and laya-multilingual-noulxp?
caliber-flex-1b is from onepass and laya-multilingual-noulxp from Convai Innovations. Both have open weights you can download and run. Both answer choice, noul and score questions. Only laya-multilingual-noulxp answers classify and route. caliber-flex-1b is licensed other; laya-multilingual-noulxp, apache-2.0.
Which is more accurate, caliber-flex-1b or laya-multilingual-noulxp?
Neither publishes an accuracy figure. Test both on your own labelled examples.
Which is cheaper, caliber-flex-1b or laya-multilingual-noulxp?
caliber-flex-1b: Free (open weights). laya-multilingual-noulxp: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run caliber-flex-1b or laya-multilingual-noulxp locally?
Yes, both: systemone pull onepass/caliber-flex-1b and systemone pull convai-innovations/laya-multilingual-noulxp download the weights.
Measured by System One Models on 2026-10-05: one question per request, 4 threads of a Xeon Gold 6342
