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
- Robot build test: GPT-6 Astra stabilizes two-board structure, Claude Fable 5.2 falls short — qinzytech · 2026-11-12
- Zvi dissects Anthropic's latest system card, disputing the autonomy threshold call — Don't Worry About the Vase (Zvi) · 2026-11-12
- Unsloth ships Qwen3.8-27B Dynamic V3.1 GGUFs with 5-10% accuracy gains — danielhanchen · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12
- Gemini re-renders images as text when vision is removed, dropping only 6% WSR — zacharynado · 2026-11-12
- Bare-harness coding benchmark: Fable 5.2 best overall, Gemini 4 Carbon best value — Semantic_meaning · 2026-11-12