A typed-decision layer for Google's DiffusionGemma, from David Villalón at Maisa AI. It compiles a request into a small answer canvas, runs one denoising read on patched vLLM and reads the probabilities of the allowed labels, for text, images and images offered as options.
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, score, noul
choice, score, noul, classify, route
Architecture
djev
julia
Fine-tuned from
google/diffusiongemma-26b-a4b-it
jhu-clsp/mmbert-small
License
apache-2.0
apache-2.0
Availability
Open weights + hosted API
Open weights
Hosted by
Maisa
—
Input price
$0.035/MTok
—
Decision accuracy
—
73.2%
Calibration error
—
—
Valid action rate
—
—
Median latency
—
—
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 djev and julia-1?
djev is from Maisa and julia-1 from Supersonic Labs. djev has open weights and a hosted API; julia-1 has open weights you can download and run. Both answer choice, score and noul questions. Only julia-1 answers classify and route. julia-1 is the smaller model, at 144M parameters to 26B.
Which is more accurate, djev or julia-1?
Only julia-1 publishes an accuracy figure (73.2% on typed-decisions test set (400 cases, 2,000 questions)); djev does not, so there is no comparison to make without your own test.
Which is cheaper, djev or julia-1?
djev: $0.035 / $0 per 1M, or free to self-host. julia-1: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run djev or julia-1 locally?
Yes, both: systemone pull maisa/djev and systemone pull supersonic-labs/julia-1 download the weights.
Evaluation suite
—
typed-decisions test set (400 cases, 2,000 questions)
