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 Situated World Model for fast judgment in agent loops.
Decides
choice, score, noul, classify, route
choice, route, classify
Architecture
bosun
trio-spark
Fine-tuned from
qwen/qwen3-1.7b
—
License
apache-2.0
proprietary
Availability
Open weights
Hosted API
Hosted by
—
MachineFi
Input price
—
$0.042/MTok
Decision accuracy
84.9%
—
Calibration error
0.050
—
Valid action rate
—
—
Median latency
—
—
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 trio-spark-v1?
bosun is from Hanno Labs and trio-spark-v1 from MachineFi. bosun has open weights you can download and run; trio-spark-v1 is only available as a hosted API. Both answer choice, classify and route questions. Only bosun answers score and noul. bosun is licensed apache-2.0; trio-spark-v1, proprietary.
Which is more accurate, bosun or trio-spark-v1?
Only bosun publishes an accuracy figure (84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)); trio-spark-v1 does not, so there is no comparison to make without your own test.
Which is cheaper, bosun or trio-spark-v1?
bosun: Free (open weights). trio-spark-v1: $0.042 / $0 per 1M. Open weights cost nothing per call beyond your own hardware.
Can I run bosun or trio-spark-v1 locally?
bosun yes — systemone pull hanno-labs/bosun downloads its weights. The other is only served as a hosted API.
