---
type: "raw_signal"
id: "fastino-gliner2-5-decide-3f9719"
slug: "fastino-gliner2-5-decide-3f9719"
title: "Fastino released GLiNER2.5-Decide, a 340M English model for operational text classification"
description: "Fastino released GLiNER2.5-Decide, a 340M English model for operational text classification."
retrieval_nugget: "Fastino released GLiNER2.5-Decide, a 340M English model for operational text classification."
observed_at: "2026-09-25"
record_date: "2026-09-25"
date_kind: "observed_at"
why_it_matters: "Source: https://huggingface.co/fastino/GLiNER2.5-Decide"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "huggingface.co"
topics: []
entities: []
related_patterns: []
source_url: "https://huggingface.co/fastino/GLiNER2.5-Decide"
source_urls: ["https://huggingface.co/fastino/GLiNER2.5-Decide"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:fastino-gliner2-5-decide-3f9719"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/fastino-gliner2-5-decide-3f9719/","markdown":"https://newruntime.com/signals/fastino-gliner2-5-decide-3f9719.md","json":"https://newruntime.com/signals/fastino-gliner2-5-decide-3f9719.json"}
---

# Fastino released GLiNER2.5-Decide, a 340M English model for operational text classification

## Retrieval answer

Fastino released GLiNER2.5-Decide, a 340M English model for operational text classification.

Fastino released GLiNER2.5-Decide, a 340M English model for operational text classification. The model card says callers can supply label sets at runtime for intent, routing, sentiment, priority, policy, and multi-label tagging, with several decision heads evaluated in one forward pass. It is positioned for local deployment under Apache-2.0 rather than as a general-purpose answering model.

On Fastino’s English fast-decisions benchmark—17 domains with 300 held-out examples per domain—the model card reports 60.2% average exact-match accuracy for GLiNER2.5-Decide. The card explicitly limits the model’s role: it does not reason, explain, or answer open questions. A separate multilingual variant is recommended for multilingual input.

Source: https://huggingface.co/fastino/GLiNER2.5-Decide

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)