Fastino's open-weight decision model. A DeBERTa-v3-large encoder that scores label sets supplied at runtime, answers single-label, multi-label, yes/no and ordinal questions in one pass, and extracts spans and relations.
A 0.6B replica of the System One idea trained on game environments. A Qwen3-0.6B backbone with an attention-based Choice head that scores a dynamic candidate set for Maze, Snake, ViZDoom and position prediction, shipped with its full training pipeline.
Decides
choice, score, noul, classify, extract, route
choice, noul, score
Architecture
gliner2
nanojev
Fine-tuned from
fastino/gliner2-large-v1
qwen/qwen3-0.6b
License
apache-2.0
mit
Availability
Open weights + hosted API
Open weights
Hosted by
Fastino
—
Input price
—
—
Decision accuracy
60.2%
—
Calibration error
—
—
Valid action rate
—
—
Median latency
38.3 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 gliner2-5-decide and nanojev?
gliner2-5-decide is from Fastino Labs and nanojev from TianyuCodings. gliner2-5-decide has open weights and a hosted API; nanojev has open weights you can download and run. Both answer choice, score and noul questions. Only gliner2-5-decide answers classify, extract and route. gliner2-5-decide is the smaller model, at 340M parameters to 600M. gliner2-5-decide is licensed apache-2.0; nanojev, mit.
Which is more accurate, gliner2-5-decide or nanojev?
Only gliner2-5-decide publishes an accuracy figure (60.2% on Fastino fast-decisions suite (17 datasets)); nanojev does not, so there is no comparison to make without your own test.
Which is cheaper, gliner2-5-decide or nanojev?
gliner2-5-decide: Hosted, price not published, or free to self-host. nanojev: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Can I run gliner2-5-decide or nanojev locally?
Yes, both: systemone pull fastino-labs/gliner2-5-decide and systemone pull tianyu-codings/nanojev download the weights.
