An open family of System One models. A LoRA adapter plus a pointer head on a frozen Qwen base returns a distribution per typed question in one forward pass, serves TypeSafe's /v1/systemone contract, and ships a fitted temperature with every checkpoint.
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
kev
winnow
Fine-tuned from
qwen/qwen3.5-4b-base
google/gemma-4-12b-it
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
83.8%
85.7%
Calibration error
0.042
—
Valid action rate
—
—
Median latency
—
143 ms
p95 latency
—
—
Evaluation suite
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 kev and winnow?
kev is from Jared Palmer and winnow from EldanRing. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. winnow reads up to 64K tokens of state, against 8K tokens for kev. kev is the smaller model, at 4.0B parameters to 12B.
Which is more accurate, kev or winnow?
They report on different suites — kev 83.8% on transfer-v4 (locked, out of domain), 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, kev or winnow?
kev: Free (open weights). winnow: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run kev or winnow locally?
Yes, both: systemone pull jared-palmer/kev and systemone pull eldanring/winnow download the weights.
