Caliber Flex 5B by OnePass. Decision-only model, exactly 5,000,000,000 parameters.
Omar (kouhxp)'s CPU decision model: a Qwen3.5-0.8B fine-tune shipped as GGUF for llama.cpp that answers yes/no, choice and score questions with a probability per option plus a 'none of these' reject probability, served by a local Jev-style HTTP runtime.
Decides
choice, noul, score
choice, score, noul, classify, route
Architecture
llm
gutsy
Fine-tuned from
qwen/qwen3.5-4b-base
qwen/qwen3.5-0.8b
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 gutsy?
caliber-flex-5b is from onepass and gutsy from Omar (kouhxp). Both have open weights you can download and run. Both answer choice, noul and score questions. Only gutsy answers classify and route. caliber-flex-5b is licensed other; gutsy, apache-2.0.
Which is more accurate, caliber-flex-5b or gutsy?
Only gutsy publishes an accuracy figure (73.2% on JevBench public set (231 items; 169 correct), the maker's own run with Q8_0); caliber-flex-5b does not, so there is no comparison to make without your own test.
Which is cheaper, caliber-flex-5b or gutsy?
caliber-flex-5b: Free (open weights). gutsy: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run caliber-flex-5b or gutsy locally?
Yes, both: systemone pull onepass/caliber-flex-5b and systemone pull kouhxp/gutsy download the weights.
—
JevBench public set (231 items; 169 correct), the maker's own run with Q8_0
