Caliber Flex 5B by OnePass. Decision-only model, exactly 5,000,000,000 parameters.
A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
llm
julia
Fine-tuned from
qwen/qwen3.5-4b-base
jhu-clsp/mmbert-small
License
caliber-flex-non-commercial-1.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
—
73.2%
Calibration error
—
—
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-5b and julia-1?
caliber-flex-5b is from onepass and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, noul and score questions. Only julia-1 answers classify and route. caliber-flex-5b is licensed other; julia-1, apache-2.0.
Which is more accurate, caliber-flex-5b or julia-1?
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); caliber-flex-5b does not, so there is no comparison to make without your own test.
Which is cheaper, caliber-flex-5b or julia-1?
caliber-flex-5b: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run caliber-flex-5b or julia-1 locally?
Yes, both: systemone pull onepass/caliber-flex-5b and systemone pull supersonic-labs/julia-1 download the weights.
typed-decisions test set (400 cases, 2,000 questions)
