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 Gemma 4 12B fine-tune for typed decisions that also chats and reads images. Ships as GGUF for llama.cpp, holds a 64K context on a 16 GB GPU, and serves /v1/systemone next to /v1/chat/completions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
openthai
winnow
Fine-tuned from
qwen/qwen3.5-0.8b-base
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
74.3%
85.7%
Calibration error
—
—
Valid action rate
—
—
Median latency
40 ms
143 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 winnow?
openthai-systemone is from iApp Technology and winnow from EldanRing. 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 12B.
Which is more accurate, openthai-systemone or winnow?
They report on different suites — openthai-systemone 74.3% on Bespoke public subsets (13, macro average), winnow 85.7% on JevBench public subset (231 items), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, openthai-systemone or winnow?
openthai-systemone: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, openthai-systemone or winnow?
By their publishers’ figures, openthai-systemone answers in about 40 ms at the median and winnow in about 143 ms — measured on different hardware, so treat it as a rough guide.
Can I run openthai-systemone or winnow locally?
Yes, both: systemone pull iapp-technology/openthai-systemone and systemone pull eldanring/winnow download the weights.
