Skip to main content
Decision modelOpen source

Decider 2B Vision

Mapika

Released
-
Data date
September 24, 2026
Model class
Typed decision model
Result
Choice, Noul and Score as probability distributions
Access
Local

Decider 2B Vision adds images to the Decider readout. You provide an image, text, and typed questions, and the 1.9-billion-parameter checkpoint returns probabilities over your supplied options. Its context window holds 32,000 tokens.

For text-only inputs, Decider 2B is the counterpart. The vision variant adds an image to a text question, for example when inspecting a frame.

Specifications and access

SpecificationValue and source
Model class
Typed decision modelSource
Access
LocalSource
Model ID
Mapika/decider-2b-visionSource
Input
Image, text and typed questionsSource
Output
Structured probabilities, no text generationSource
Result
Choice, Noul and Score as probability distributionsSource
Parameters
2 billionSource
Context window
32,000 tokensSource
License
Apache-2.0Source
Scope
Local readout without autoregressive text generation.Source
Notes
The model is intended for structured decisions, not multi-step text answers.Source
Base model
Qwen3.5-2B VisionSource
Choice options
2-255 per questionSource