Frontier Infra's open decision model. A LoRA merged into Qwen3.8-27B (thinking off) that answers one typed question per forward pass with a probability over the option labels, served through AINode's TypeSafe-compatible /v1/systemone.
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
jebadiah
winnow
Fine-tuned from
qwen/qwen3.8-27b
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
86.6%
85.7%
Calibration error
0.113
—
Valid action rate
—
—
Median latency
—
143 ms
p95 latency
—
—
Evaluation suite
JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier
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 jebadiah and winnow?
jebadiah is from Frontier Infra and winnow from EldanRing. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. winnow is the smaller model, at 12B parameters to 27B.
Which is more accurate, jebadiah or winnow?
They report on different suites — jebadiah 86.6% on JevBench public set (231 items), maker's run with the v1.4.2 harness; ECE on the hard tier, 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, jebadiah or winnow?
jebadiah: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jebadiah or winnow locally?
Yes, both: systemone pull frontier-infra/jebadiah and systemone pull eldanring/winnow download the weights.
