Hanno Labs' small calibrated decision model. A LoRA on Qwen3-1.7B plus trained decision-token embeddings with stable slots, returning the full distribution over up to 255 caller-defined choices and a null slot for Choice, Score and Noul questions.
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
bosun
simple-jev
Fine-tuned from
qwen/qwen3-1.7b
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
84.9%
—
Calibration error
0.050
—
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 bosun and simple-jev?
bosun is from Hanno Labs and simple-jev from Featherless AI. bosun 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, bosun or simple-jev?
Only bosun publishes an accuracy figure (84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)); simple-jev does not, so there is no comparison to make without your own test.
Which is cheaper, bosun or simple-jev?
bosun: 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 bosun or simple-jev locally?
Yes, both: systemone pull hanno-labs/bosun and systemone pull featherless-ai/simple-jev download the weights.
—
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
