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.
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
kev
lumma-fev
Fine-tuned from
qwen/qwen3.5-4b-base
frontiersmind/lumma-0.6b-base
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
83.8%
64.0%
Calibration error
0.042
—
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 kev and lumma-fev?
kev is from Jared Palmer and lumma-fev from FrontiersMind. Both have open weights you can download and run. Both answer choice, score and noul questions. Only kev answers classify and route. lumma-fev is the smaller model, at 649M parameters to 4.0B.
Which is more accurate, kev or lumma-fev?
They report on different suites — kev 83.8% on transfer-v4 (locked, out of domain), 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, kev or lumma-fev?
kev: Free (open weights). lumma-fev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run kev or lumma-fev locally?
Yes, both: systemone pull jared-palmer/kev and systemone pull frontiersmind/lumma-fev download the weights.
