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.
A Gemma 4 12B fine-tune for typed decisions that also chats and reads images. Ships as GGUF for llama.cpp, holds a 64K context on a 16 GB GPU, and serves /v1/systemone next to /v1/chat/completions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
bosun
winnow
Fine-tuned from
qwen/qwen3-1.7b
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
84.9%
85.7%
Calibration error
0.050
—
Valid action rate
—
—
Median latency
—
143 ms
p95 latency
—
—
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
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 winnow?
bosun is from Hanno Labs and winnow from EldanRing. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. bosun is the smaller model, at 2.0B parameters to 12B.
Which is more accurate, bosun or winnow?
They report on different suites — bosun 84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families), winnow 85.7% on JevBench public subset (231 items), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bosun or winnow?
bosun: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bosun or winnow locally?
Yes, both: systemone pull hanno-labs/bosun and systemone pull eldanring/winnow download the weights.
