GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Danielbrdz
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Danielbrdz
Model Tree
google/gemma-4-31B-it
Input Modalities
Output Modalities
Supported Functionality
Barcenas 31b Fable
Basado en Gemma 4 31b it de Google y entranado con el dataset agentic-distill-fable-5-sft
Es mi modelo más grande y potente que he hecho hasta la fecha y entrenado con datos de alta calidad directamente de Claude Fable 5 para uso de agentes
Con está combinación se puede tener un LLM que se puede ejecutar una sola GPU y para uso agéntico de manera local y privado de manera eficiente, claro si tienes los requisitos de hardware
Barcenas 31b Fable
Based on Google's Gemma 4 31b it and trained with the agentic-distill-fable-5-sft dataset.
This is my largest and most powerful model to date, trained with high-quality data directly from Claude Fable 5 for agent use.
With this combination, you can have an LLM that can run on a single GPU and implement agentic use locally and privately, provided you meet the hardware requirements.
Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽