Small open typed-decision model with calibrated probabilities, first-class Nepali coverage.
Featherless AI's open server that turns a stock Hugging Face language model into a typed-decision endpoint. It reads the next-token logits for each question and builds the Choice, Score or Noul answer itself; no classifier head is trained and no JSON is generated.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
mira
simple-jev
Fine-tuned from
jhu-clsp/mmbert-small
google/gemma-4-26b-a4b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights + hosted API
Hosted by
—
Featherless AI
Input price
—
—
Decision accuracy
74.5%
—
Calibration error
0.025
—
Valid action rate
100.0%
—
Median latency
30 ms
—
p95 latency
43 ms
—
Evaluation suite
s1-decision-bench
—
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 simple-jev?
mira is from SAGEA and simple-jev from Featherless AI. mira has open weights you can download and run; simple-jev has open weights and a hosted API. Both answer choice, score, noul, classify and route questions.
Which is more accurate, mira or simple-jev?
Only mira publishes an accuracy figure (74.5% on s1-decision-bench); simple-jev does not, so there is no comparison to make without your own test.
Which is cheaper, mira or simple-jev?
mira: Free (open weights). simple-jev: Hosted, price not published, or free to self-host. Open weights cost nothing per call beyond your own hardware.
Can I run mira or simple-jev locally?
Yes, both: systemone pull sagea/mira and systemone pull featherless-ai/simple-jev download the weights.
