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.
Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
kev
mira
Fine-tuned from
qwen/qwen3.5-4b-base
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
83.8%
74.5%
Calibration error
0.042
0.025
Valid action rate
—
100.0%
Median latency
—
30 ms
p95 latency
—
43 ms
Evaluation suite
transfer-v4 (locked, out of domain)
s1-decision-bench
Latest version
2026.09
0.1.4
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 kev and mira?
kev is from Jared Palmer and mira from SAGEA. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
Which is more accurate, kev or mira?
They report on different suites — kev 83.8% on transfer-v4 (locked, out of domain), mira 74.5% on s1-decision-bench — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, kev or mira?
kev: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run kev or mira locally?
Yes, both: systemone pull jared-palmer/kev and systemone pull sagea/mira download the weights.