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.
FrontiersMind's decision model on a base it pre-trained from scratch. Each question reads the state and its own tokens once and a 256-dimension pointer head scores the options; Choice and Score take up to 255 entries, and nothing is generated.
Decides
choice, score, noul, classify, route
choice, score, noul
Architecture
decider
lumma-fev
Fine-tuned from
qwen/qwen3.5-2b-base
frontiersmind/lumma-0.6b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
75.2%
64.0%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
45.8 ms
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 lumma-fev?
decider is from Mapika and lumma-fev from FrontiersMind. Both have open weights you can download and run. Both answer choice, score and noul questions. Only decider answers classify and route. decider reads up to 32K tokens of state, against 8K tokens for lumma-fev. lumma-fev is the smaller model, at 649M parameters to 1.9B.
Which is more accurate, decider or lumma-fev?
They report on different suites — decider 75.2% on Decider regression set, 28 held-out tasks (decider-2b v11), lumma-fev 64.0% on typed-decisions (maker's table; split not stated) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decider or lumma-fev?
decider: Free (open weights). lumma-fev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run decider or lumma-fev locally?
Yes, both: systemone pull mapika/decider and systemone pull frontiersmind/lumma-fev download the weights.
