Fastino Releases GLiNER2.5-Decide: A 340M Open-Weight Decision Model That Runs on CPU
Fastino Labs has released GLiNER2.5-Decide, a 340M-parameter open-weight decision model. It takes text and a schema of typed questions and returns structured answers. Each answer comes with a probability distribution, a confidence score, and constraint-feasibility metadata. It targets the frequent judgment calls inside agent pipelines: routing, triage, tool selection, and guardrails. Is it deployable? Yes, the weights ship under Apache 2.0 and install with pip install gliner2. They run on CP
Get smart on it
Fastino Labs released GLiNER2.5-Decide, a 340-million-parameter open-weight model that classifies text against a schema of typed questions and returns structured answers with confidence scores and constraint-feasibility metadata. The model is designed for operational decisions in AI agent pipelines, such as routing, triage, tool selection, and guardrails, and runs on CPU, GPU, or in air-gapped environments. Unlike generative models, it produces no generated tokens and uses a two-stage pipeline where an encoder scores permitted answers and a constrained decoder applies rules to ensure consistent joint outputs across related questions. In benchmarks on an internal suite of 5,100 test examples across 17 datasets, the model achieved 60.1% exact-match accuracy and demonstrated practical latency of 167.3 milliseconds on CPU for short inputs.
Related news
Google Research Moves Federated Learning Into TEEs: Gboard Now Trains With Externally Verifiable Differential Privacy
Google Research has announced a next-generation Federated Learning (FL) system built on Trusted Execution Environments (TEEs). The research team claims externally verifiable central differential privacy (DP) guarantees for FL for the first time. What Problem Does TEE-Based Federated Learning Solve? Google introduced Federated Learning FL in 2017. It powers next-word prediction and Smart Compose on Gboard, reply suggestions in Google Messages, and Smart Text Selection in Android. Earli
Aleph Alpha Releases Kolibri: A 78.1B Open-Weight English-German MoE Model With Only 3.46B Active Parameters
Aleph Alpha has released Kolibri, an open-weight Mixture-of-Experts (MoE) language model built for German and English. Kolibri has 78.1B total parameters but activates only 3.46B, or 4.4%, per token. It accepts up to 1,048,576 tokens of context, lets users set reasoning effort per request, and ships under the Apache 2.0 license on Hugging Face. The target is sovereign deployment in regulated sectors such as public administration, industry and aerospace. Is it deployable? Yes. The FP8 checkpo
