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.
A local, Jev-compatible decision model from Rizzo AI Academy. XHToken's Spark-X2.5-4B with a merged typed-decisions LoRA, run on llama.cpp; yes/no, choice and score questions share one prefill of the state and are read from the answer-letter logits. No text is generated.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
openthai
rizzo-flow
Fine-tuned from
qwen/qwen3.5-0.8b-base
xhtoken/spark-x2.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
74.3%
64.8%
Calibration error
—
0.112
Valid action rate
—
—
Median latency
40 ms
195 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 openthai-systemone and rizzo-flow?
openthai-systemone is from iApp Technology and rizzo-flow from Rizzo AI Academy. 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, openthai-systemone or rizzo-flow?
They report on different suites — openthai-systemone 74.3% on Bespoke public subsets (13, macro average), rizzo-flow 64.8% on LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, openthai-systemone or rizzo-flow?
openthai-systemone: Free (open weights). rizzo-flow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, openthai-systemone or rizzo-flow?
By their publishers’ figures, openthai-systemone answers in about 40 ms at the median and rizzo-flow in about 195 ms — measured on different hardware, so treat it as a rough guide.
Can I run openthai-systemone or rizzo-flow locally?
Yes, both: systemone pull iapp-technology/openthai-systemone and systemone pull rizzo-ai-academy/rizzo-flow download the weights.
—
Evaluation suite
Bespoke public subsets (13, macro average)
LocalLLaMA/typed-decisions test split (400 cases, 2,000 decisions), Q8_0
