An open Jev-style LoRA on Qwen3.5-9B from Bespoke Labs, trained on 2,676 contrastively curated examples to score the allowed answer tokens directly for enums, booleans and rubric levels. Recipe, data and a public benchmark suite are released with it.
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, noul, score, classify, route
choice, score, noul, classify, route
Architecture
nimble
openthai
Fine-tuned from
qwen/qwen3.5-9b
qwen/qwen3.5-0.8b-base
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Bespoke Labs
—
Input price
—
—
Decision accuracy
90.1%
74.3%
Calibration error
0.054
—
Valid action rate
—
—
Median latency
106 ms
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 bespoke-nimble-9b and openthai-systemone?
bespoke-nimble-9b is from Bespoke Labs and openthai-systemone from iApp Technology. bespoke-nimble-9b has open weights and a hosted API; openthai-systemone has open weights you can download and run. Both answer choice, noul, score, classify and route questions. openthai-systemone is the smaller model, at 800M parameters to 9.0B.
Which is more accurate, bespoke-nimble-9b or openthai-systemone?
They report on different suites — bespoke-nimble-9b 90.1% on Bespoke held-out set (324 examples), 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, bespoke-nimble-9b or openthai-systemone?
bespoke-nimble-9b: Hosted, price not published, or free to self-host. openthai-systemone: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, bespoke-nimble-9b or openthai-systemone?
By their publishers’ figures, openthai-systemone answers in about 40 ms at the median and bespoke-nimble-9b in about 106 ms — measured on different hardware, so treat it as a rough guide.
Can I run bespoke-nimble-9b or openthai-systemone locally?
Yes, both: systemone pull bespoke-labs/bespoke-nimble-9b and systemone pull iapp-technology/openthai-systemone download the weights.
