A family of open System One models by Mark Marosi, decider-0.8b, decider-2b, decider-4b and decider-35b-a3b on Qwen3.5 bases, that softmax letter logits at an answer slot. This page carries decider-2b v11.
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
decider
simple-jev
Fine-tuned from
qwen/qwen3.5-2b-base
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
75.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
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 decider and simple-jev?
decider is from Mapika and simple-jev from Featherless AI. decider 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, decider or simple-jev?
Only decider publishes an accuracy figure (75.2% on Decider regression set, 28 held-out tasks (decider-2b v11)); simple-jev does not, so there is no comparison to make without your own test.
Which is cheaper, decider or simple-jev?
decider: 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 decider or simple-jev locally?
Yes, both: systemone pull mapika/decider and systemone pull featherless-ai/simple-jev download the weights.
