340M Open-Weight Decision Model GLiNER2.5-Decide Runs in Browser at ~100ms on a MacBook

nicodotdev · x · 2026-09-25

Fastino released GLiNER2.5-Decide, a 340M-parameter open-weight encoder model for fast, deterministic classification. It jointly decodes user-defined typed questions and rules, returning structured decisions with probability distributions and confidence scores. On Fast Decisions, an internal suite built from 17 datasets covering routing, triage, sentiment, and content understanding, it leads on 9 of 17 against similar decision models. The community has already ported it to ONNX with a WebGPU demo in the open-jev project: 4 typed decisions in 100ms on a MacBook, with text never leaving the browser tab.

Related event: Fastino open-sources 340M decision model GLiNER2.5-Decide, beating LLM routing(4 posts)→

Original post →

More from Models

Models channel →