Caliber Flex 1B by OnePass. Decision-only model, exactly 1,000,000,000 parameters.
An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
llm
kev
Fine-tuned from
qwen/qwen3.5-0.8b-base
qwen/qwen3.5-4b-base
License
caliber-flex-non-commercial-1.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
83.8%
Calibration error
—
0.042
Valid action rate
—
—
Median latency
—
—
p95 latency
—
—
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 kev?
caliber-flex-1b is from onepass and kev from Jared Palmer. Both have open weights you can download and run. Both answer choice, noul and score questions. Only kev answers classify and route. caliber-flex-1b is licensed other; kev, apache-2.0.
Which is more accurate, caliber-flex-1b or kev?
Only kev publishes an accuracy figure (83.8% on transfer-v4 (locked, out of domain)); caliber-flex-1b does not, so there is no comparison to make without your own test.
Which is cheaper, caliber-flex-1b or kev?
caliber-flex-1b: Free (open weights). kev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run caliber-flex-1b or kev locally?
Yes, both: systemone pull onepass/caliber-flex-1b and systemone pull jared-palmer/kev download the weights.
