Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
A 4B decision model fine-tuned from Qwen3.5-4B-Base. A state and typed questions (choice, yes/no, score) go in; a temperature-calibrated probability for every option comes out of one pass, through a self-hosted /v1/systemone-compatible server. Apache-2.0 weights and code.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
mira
wald
Fine-tuned from
jhu-clsp/mmbert-small
qwen/qwen3.5-4b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
61.3%
88.3%
Calibration error
0.083
0.045
Valid action rate
100.0%
—
Median latency
30 ms
33 ms
p95 latency
43 ms
168 ms
Evaluation suite
s1-decision-bench
JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard
Latest version
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 mira and wald?
mira is from SAGEA and wald from ORG2 AI. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions.
Which is more accurate, mira or wald?
They report on different suites — mira 61.3% on s1-decision-bench, wald 88.3% on JevBench public set (231 items; 204 correct), maker's run with the JevBench CLI, v1.2, effort none; items used as a development scoreboard — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, mira or wald?
mira: Free (open weights). wald: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, mira or wald?
By their publishers’ figures, mira answers in about 30 ms at the median and wald in about 33 ms — measured on different hardware, so treat it as a rough guide.
Can I run mira or wald locally?
Yes, both: systemone pull sagea/mira and systemone pull org2ai/wald download the weights.
0.1.5
1.2.0
Variants
—
Dockerfile, LICENSE, NOTICE, model-files, reference, server
