Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
A 340M model that takes new labels without retraining is small enough to run on CPU next to an agent, and handles the classification steps that are otherwise sent to a large LLM. Apache-2.0 weights make it usable commercially.
Where this stands now
GLiNER2.5-Decide ranks #5 of 66 tracked Models items by composite score (7.9 against a section median of 4.9). The section currently carries 58 Bronze, 5 Silver, 3 Gold. RepoRadar has retained observations for this record since 2026-09-26 (14 days in the current window). Signal extremes versus the section: momentum at the 91th percentile; novelty at the 86th percentile.
Who should use it
Who should skip it
Consider GLiNER2.5-Decide lower priority if you already have a working solution in this category.
About this signal
GLiNER2.5-Decide is tracked by RepoRadar as a model release in the Models section. First seen 2026-09-26; the source record was last checked on 2026-09-26. The current verdict is 'try now' with a Silver tier and Easy setup difficulty. GLiNER2.5-Decide leads on workflow potential (9.0) and setup ease (8.8); its lowest signal is open-source/build quality (6.8), so factor that in before investing setup time. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The GLiNER2.5-Decide record combines a 7.9/10 composite score with separate popularity (100.0), risk (none), and setup (Easy) signals. See the scoring methodology for the current weights and evidence definitions.
Putting this into practice? Read Local AI vs. hosted APIs: how to choose for the checklist behind this score.
Risk explanation
No inherent user-impacting risk is flagged from the captured evidence.