The most-downloaded open System One reproduction. Merged Qwen3.5 fine-tunes, trained on about 95 public decision sets, then calibration-aware RL and a rank-64 LoRA, that softmax letter logits at an answer slot.
A Gemma 4 12B fine-tune for typed decisions that also chats and reads images. Ships as GGUF for llama.cpp, holds a 64K context on a 16 GB GPU, and serves /v1/systemone next to /v1/chat/completions.
Decides
choice, score, noul, classify, route
choice, score, noul, classify, route
Architecture
decider
winnow
Fine-tuned from
qwen/qwen3.5-2b-base
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
80.2%
85.7%
Calibration error
0.038
—
Valid action rate
—
—
Median latency
3.2 ms
143 ms
p95 latency
—
—
Evaluation suite
Decider 67-task regression set
JevBench public subset (231 items), Q8_0
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 winnow?
decider is from Mapika and winnow from EldanRing. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. decider is the smaller model, at 2.0B parameters to 12B.
Which is more accurate, decider or winnow?
They report on different suites — decider 80.2% on Decider 67-task regression set, winnow 85.7% on JevBench public subset (231 items), Q8_0 — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, decider or winnow?
decider: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, decider or winnow?
By their publishers’ figures, decider answers in about 3.2 ms at the median and winnow in about 143 ms — measured on different hardware, so treat it as a rough guide.
Can I run decider or winnow locally?
Yes, both: systemone pull mapika/decider and systemone pull eldanring/winnow download the weights.