A family of open System One models by Mark Marosi, decider-0.8b, decider-2b, decider-4b and decider-35b-a3b on Qwen3.5 bases, that softmax letter logits at an answer slot. This page carries decider-2b v11.
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
decider
julia
Fine-tuned from
qwen/qwen3.5-2b-base
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
75.2%
73.2%
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 julia-1?
decider is from Mapika and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider reads up to 32K tokens of state, against 8K tokens for julia-1. julia-1 is the smaller model, at 144M parameters to 1.9B.
Which is more accurate, decider or julia-1?
They report on different suites — decider 75.2% on Decider regression set, 28 held-out tasks (decider-2b v11), 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, decider or julia-1?
decider: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or julia-1 locally?
Yes, both: systemone pull mapika/decider and systemone pull supersonic-labs/julia-1 download the weights.
