granite-3.1-2b-instruct-quantized.w4a16

Name: granite-3.1-2b-instruct-quantized.w4a16
Author: RedHatAI

2B open-weight LLM by RedHatAI

Live

Open / InstallLast updated August 22, 2026

Description

granite-3.1-2b-instruct-quantized.w4a16 is an open-weight text-generation model with roughly 2B parameters published by RedHatAI on the Hugging Face Hub. It has 49,031 downloads. Runs with transformers.

Author

RedHatAI

Platform

api

Pricing model

free

Capabilities

Text generation
Conversational
Library: transformers
2B parameters