Hugging Face · #500

ibm-granite/granite-4.2-30b

ibm-granite/granite-4.2-30b is a 29.3B text-generation model on Hugging Face. Run locally: llama-cli -hf ibm-granite/granite-4.2-30b or ollama run hf.co/ibm-granite/granite-4.2-30b. 135 Hugging Face likes (#500 in this directory).

Model
https://huggingface.co/ibm-granite/granite-4.2-30b
Author
ibm-granite (org)
Likes
135
Downloads (30 days)
39,483
Task
text-generation
Library
transformers
License
apache-2.0
Parameters
29.3B
Gated
No
Created
2026-08-07
Last modified
2026-09-04
Base models
ibm-granite/granite-4.1-30b-base
Snapshot
2026-10-29

Run it locally.

Shadowfetch Linux is a Debian testing desktop with KDE Plasma, local AI tools, and ShadowCode. ShadowCode's bundled llama.cpp runs GGUF models; you can also use llama.cpp or Ollama from the terminal.

llama.cpp

llama-cli -hf ibm-granite/granite-4.2-30b

Ollama

ollama run hf.co/ibm-granite/granite-4.2-30b

These commands work when this repo, or a GGUF quant of it, publishes GGUF weights. They do not invent a quant name. For safetensors-only repos, convert with llama.cpp or use a GGUF repo on the Hub.

ShadowCode prompt.

Paste this into ShadowCode after you open Settings › Local models.

In Settings › Local models, run ibm-granite/granite-4.2-30b only if a GGUF file is available. If the Hub repo is safetensors-only, use a GGUF quant instead of guessing a filename. Ask before downloading.

Download Shadowfetch Linux — ISO, checksum and signature.

Back to Hugging Face models · Methodology