A multimodal decision classifier over text, image, audio and video on Gemma 4 12B, fine-tuned on 30,000 questions. Returns a probability per option and generates nothing.
Qwen3.5-4B with a merged rank-16 LoRA distilled from 17,408 teacher questions and 30,000 public training rows, read out as a temperature-scaled softmax over answer-letter logits. Also in 9B, 2B and GGUF.
Decides
choice, noul, score, classify
choice, score, noul, classify, route
Architecture
jev-omni
jevk5
Fine-tuned from
google/gemma-4-12b-it
qwen/qwen3.5-4b
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.6%
78.4%
Calibration error
0.040
0.035
Valid action rate
—
—
Median latency
83 ms
13.2 ms
p95 latency
—
—
Evaluation suite
DecisionBench Medium (author's set)
JevBench public 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 jev-omni and jevk5?
jev-omni is from akhilaaa3 and jevk5 from Alibi Serikbay. Both have open weights you can download and run. Both answer choice, noul, score and classify questions. Only jevk5 answers route. jevk5 is the smaller model, at 4.0B parameters to 12B.
Which is more accurate, jev-omni or jevk5?
They report on different suites — jev-omni 87.6% on DecisionBench Medium (author's set), jevk5 78.4% on JevBench public hard tier — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, jev-omni or jevk5?
jev-omni: Free (open weights). jevk5: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Which is faster, jev-omni or jevk5?
By their publishers’ figures, jevk5 answers in about 13.2 ms at the median and jev-omni in about 83 ms — measured on different hardware, so treat it as a rough guide.
Can I run jev-omni or jevk5 locally?
Yes, both: systemone pull akhilaaa3/jev-omni and systemone pull alibi-serikbay/jevk5 download the weights.
