All models

COMPARE

Put models side by side.

What each one decides, how well calibrated it is, how fast it answers and what it costs to pull. Up to 4 at a time; the better value in each row is marked.

Propertyiapp-technology/openthai-systemone
SummaryA 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.
Decideschoice, score, noul, classify, route
Architectureopenthai
Fine-tuned fromqwen/qwen3.5-0.8b-base
Licenseapache-2.0
AvailabilityOpen weights
Hosted by—
Input price—
Decision accuracy74.3%
Calibration error—
Valid action rate—
Median latency40 ms
p95 latency—
Evaluation suiteBespoke public subsets (13, macro average)
Latest version0.3.0
Variants—
Size of latest version1.4 GB
Files2
Downloads0
Stars0
Tagssystem-one, thai, multilingual, qwen, 0.8b
UpdatedSep 25, 2026