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.
A Thai-and-English System One model. Qwen3.5-0.8B continued-pretrained on about 5B Thai tokens, its language-model head replaced by a 256-way slot head (slot 255 abstains), trained on 2–3M decision examples and temperature-calibrated per question type.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
kev
openthai
Fine-tuned from
qwen/qwen3.5-4b-base
qwen/qwen3.5-0.8b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
83.8%
74.3%
Calibration error
0.042
—
Valid action rate
—
—
Median latency
—
40 ms
p95 latency
—
—
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 openthai-systemone?
kev is from Jared Palmer and openthai-systemone from iApp Technology. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. openthai-systemone is the smaller model, at 800M parameters to 4.0B.
Which is more accurate, kev or openthai-systemone?
They report on different suites — kev 83.8% on transfer-v4 (locked, out of domain), openthai-systemone 74.3% on Bespoke public subsets (13, macro average) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, kev or openthai-systemone?
kev: Free (open weights). openthai-systemone: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run kev or openthai-systemone locally?
Yes, both: systemone pull jared-palmer/kev and systemone pull iapp-technology/openthai-systemone download the weights.
