A family of open System One models by Mark Marosi that softmax option-letter logits at an answer slot: decider-0.8b, 2b, 4b and 35b-a3b on Qwen3.5 bases, decider-12b on Gemma-4-12B-it, and training-free readouts of larger chat models. This page carries decider-2b v11.
DecisionTune's 395M decision model: ModernBERT-large fine-tuned with a 4 KB scoring head that scores a marker per option, answering a choice or yes/no question in one encoder pass with a probability for every option. Runs locally on CPU or GPU via PyTorch, MLX or ONNX.
Decides
choice, score, noul, classify, route
choice, noul, route, classify
Architecture
decider
decisiontune
Fine-tuned from
qwen/qwen3.5-2b-base
answerdotai/modernbert-large
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
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 decisiontune?
decider is from Mapika and decisiontune from DecisionTune. Both have open weights you can download and run. Both answer choice, noul, classify and route questions. Only decider answers score. decider reads up to 32K tokens of state, against 8K tokens for decisiontune. decisiontune is the smaller model, at 395M parameters to 1.9B.
Which is more accurate, decider or decisiontune?
Only decider publishes an accuracy figure (75.2% on Decider regression set, 28 held-out tasks (decider-2b v11)); decisiontune does not, so there is no comparison to make without your own test.
Which is cheaper, decider or decisiontune?
decider: Free (open weights). decisiontune: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or decisiontune locally?
Yes, both: systemone pull mapika/decider and systemone pull decision-tune/decisiontune download the weights.
