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.
More from Models
- OpenCode sitemap leaks GLM-5.5 Flash, GLM-5.4, Kimi K4, DeepSeek V4.1 Pro — teortaxesTex · 2026-09-25
- Open-source AI weekly: Xiaomi MiMo-V2.6-Pro tops open leaderboard at 1/45th of Opus 5's cost — 0xsachi · 2026-09-25
- Paste two AI plans into each other's threads and both will always say the other plan is better — DesignMike2020 · 2026-09-25
- Same Prompt Test: Claude Opus 5.5 Crushes GPT at Motion Graphics Video Design — thisiskp_ · 2026-09-25
- Gemini 4 likely landing next month as Google ships coding models every 3-4 weeks — haider1 · 2026-09-25
- Unverified demo claims GLM-5.3-Flash hits 240 tok/s in a single stream — SIGKITTEN · 2026-09-25