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 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
bosun
julia
Fine-tuned from
qwen/qwen3-1.7b
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
84.9%
73.2%
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 julia-1?
bosun is from Hanno Labs and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. julia-1 is the smaller model, at 144M parameters to 2.0B.
Which is more accurate, bosun or julia-1?
They report on different suites — bosun 84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families), julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, bosun or julia-1?
bosun: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run bosun or julia-1 locally?
Yes, both: systemone pull hanno-labs/bosun and systemone pull supersonic-labs/julia-1 download the weights.
Evaluation suite
DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)
typed-decisions test set (400 cases, 2,000 questions)
