AIBackends v0.6.0: Run GLiNER2.5 Extraction on CPU

Melvin Vivas · X post · 2026-08-26 · Open on X

Topics: AI Dev Tools & Productivity, LLM Fundamentals · Level: intermediate

Summary

Melvin Vivas released v0.6.0 of AIBackends, his open-source Python library for running AI tasks locally. This version supports Fastino Labs' GLiNER2.5 models, which run on CPU. The quoted Fastino post lists what GLiNER2.5 can do: long-context extraction and classification, unlimited span length, span attributes, constrained classification and joint information extraction.

Key points

• AIBackends is a Python library for running AI tasks locally. It is available on PyPI, and this release is version 0.6.0.
• v0.6.0 adds support for GLiNER2.5 from Fastino Labs, and it runs on CPU, so you don't need a GPU.
• GLiNER2.5 supports long-context extraction and classification with unlimited span length.
• It can extract span attributes and do constrained classification.
• It supports joint information extraction, meaning several extraction tasks in one pass.
• A Colab notebook in the repo shows how to do GLiNER2.5 extraction step by step.
• Fastino reported over 1,000 downloads of the GLiNER2.5 models in 24 hours.

Resources mentioned

• AIBackends · repo · aibackends.com · free
  Open-source API server runtime for common AI use cases that supports many models and providers (Ollama, LM Studio, OpenRouter, OpenAI, Anthropic).
  Also in: Building a production website with Opus 5.5 and TanStack (Melvin Vivas on X · notes), CamelFlow: open-source visual viewer for Apache Camel routes (Melvin Vivas on X · notes), AI Backends: A Production AI Workflow Engineering Site (Link Share) (Melvin Vivas on X · notes), Demo: Claude Opus 5.5 Generating a Motion-Graphics Video for AIBackends (Melvin Vivas on X · notes) and 16 more
• aibackends 0.6.0 on PyPI · tool · pypi.org · free
  The PyPI release of the AIBackends Python package, version 0.6.0.
• GLiNER2.5 Extraction Colab Notebook · repo · github.com · free
  An example notebook that runs GLiNER2.5 information extraction with AIBackends in Colab.
  Also in: Colab Notebook: Entity Extraction with GLiNER2.5 in aibackends (Melvin Vivas on X · notes)
• GLiNER2.5 · tool · fastino.ai · free
  Fastino Labs' models for extraction and classification that run on CPU, with long context and joint information extraction.
  Also in: Free Colab Notebooks: ModernBERT, Gemma QLoRA, GLiNER & Guardrails (Melvin Vivas on X · notes), Colab Notebook: Entity Extraction with GLiNER2.5 in aibackends (Melvin Vivas on X · notes)
• Fastino Labs (@fastinoAI) on X · person · x.com · free
  The X account of Fastino Labs, which builds GLiNER decision models and shares demos.
  Also in: GLiDE: Fastino's Decision Model with Adaptive Thinking (Melvin Vivas on X · notes), GLiDE by Fastino Labs: A Post-Trainable Reasoning Decision Model (Melvin Vivas on X · notes), GLiNER decision model demos from Fastino Labs (Melvin Vivas on X · notes), AIBackends v0.8.1 adds GLiNER2.5-Decide local classification (Melvin Vivas on X · notes) and 4 more

Try this

• Install aibackends 0.6.0 from PyPI.
• Run the GLiNER2.5 extraction Colab notebook.
• Build a pipeline that extracts entities and their attributes from documents on CPU only, using GLiNER2.5 through AIBackends.