Article may be outdated

This article is 46 days old. Some details may have changed since publication.

Ars Technica·3 min read·medium

IBM's new Granite 4.2 models ride the wave of interest in local LLMs

Samuel Axon
IBM's new Granite 4.2 models ride the wave of interest in local LLMs
✦AI Summary

IBM has released its Granite 4.2 model family, focusing on agentic capabilities and reasoning for enterprise deployment. These open-weight models are designed to be self-hosted and support complex tasks like tool usage.

Why it matters

As businesses seek more control over AI, local and self-hosted models provide a secure alternative to cloud-based LLMs for enterprise-grade reasoning tasks.

✦Dive DeeperCreate a free account to unlock

Enterprise AI IBM’s new Granite 4.2 models ride the wave of interest in local LLMs The focus is on agentic capability and predictable enterprise deployment.

114 Pulling Granite 4.2 8B via Ollama in macOS. Credit: Samuel Axon Pulling Granite 4.2 8B via Ollama in macOS. Credit: Samuel Axon Text settings Story text Size Small Standard Large Width * Standard Wide Links Standard Orange * Subscribers only Learn more Minimize to nav

IBM has rolled out the newest models in its family of open-weight large language models designed to be downloaded and self-hosted. The newly launched Granite 4.2 comes in 3B, 8B, and 30B parameter variants.

Continue reading on Headlinne

Create a free account to read the full article.

Read full article →
technologyaibusiness
✦

Get smarter about the news

Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.

Create free account

Already have an account? Sign in