Models / Perplexity Decider v1.1
Perplexity Decider v1.1
An open-weight decision checkpoint for text and images. Its supplied runtime preserves attention and calibration settings that generic text-generation serving may miss.
What it's good at
- An open-weight decision checkpoint for text and images. Its supplied runtime preserves attention and calibration settings that generic text-generation serving may miss.
Limits and caveats
- The card calls for Python 3.12+ and roughly 49 GiB for weights plus working memory. Its usage text still calls the repository private, while current metadata is public and ungated. Preserve the evaluated attention and calibration settings; benchmark gains do not establish performance on your task.
- Source reviewed on 12 October 2026. No inference, accuracy, latency, or cost tests performed by Typed Recipes.
Source reviewed · Not tested by Typed Recipes