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.
A 144M-parameter System One model on the multilingual mmBERT-small encoder. Takes a state, a question and 2 to 20 options and returns one decision with probabilities for choice, score and yes/no questions, on a CPU.
Decides
choice, noul, score, classify
choice, score, noul, classify, route
Architecture
jev-omni
julia
Fine-tuned from
google/gemma-4-12b-it
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights
Open weights
Hosted by
—
—
Input price
—
—
Decision accuracy
87.6%
73.2%
Calibration error
0.040
—
Valid action rate
—
—
Median latency
83 ms
—
p95 latency
—
—
Evaluation suite
DecisionBench Medium (author's set)
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 julia-1?
jev-omni is from akhilaaa3 and julia-1 from Supersonic Labs. Both have open weights you can download and run. Both answer choice, noul, score and classify questions. Only julia-1 answers route. julia-1 is the smaller model, at 144M parameters to 12B.
Which is more accurate, jev-omni or julia-1?
They report on different suites — jev-omni 87.6% on DecisionBench Medium (author's set), julia-1 73.2% on typed-decisions test set (400 cases, 2,000 questions) — so the numbers do not rank them. Test both on your own labelled examples.
Which is cheaper, jev-omni or julia-1?
jev-omni: Free (open weights). julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run jev-omni or julia-1 locally?
Yes, both: systemone pull akhilaaa3/jev-omni and systemone pull supersonic-labs/julia-1 download the weights.
typed-decisions test set (400 cases, 2,000 questions)
