Question 1

What is nishparadox/granite-guardian-3.2-5b-multi-harm-GGUF?

Accepted Answer

--- license: apache-2.0 base_model: ibm-granite/granite-guardian-3.2-5b tags: - gguf - granite - safety - guardrails --- # Granite Guardian 3.2 5B Multi-Harm F16 GGUF Merged model of [ibm-granite/granite-guardian-3.2-5b](https://huggingface.co/ibm-granite/granite-guardian-3.2-5b) + [ibm-granite/granite-guardian-3.2-5b-lora-harm-categories](https://huggingface.co/ibm-granite/granite-guardian-3.2-5b-lora-harm-categories) LoRA adapter. ## Usage ### Ollama ```bash ollama run hf.co/nishparadox/granite-guardian-3.2-5b-multi-harm-GGUF:F16 ``` ### llama.cpp ```bash llama-cli -m granite-guardian-3.2-5b-multi-harm-f16.gguf -p "Your prompt" ``` ## Prompt Format for Multi-Risk Detection See [original model card](https://huggingface.co/ibm-granite/granite-guardian-3.2-5b-lora-harm-categories) for full prompt template.

Question 2

What license applies to nishparadox/granite-guardian-3.2-5b-multi-harm-GGUF?

Accepted Answer

License: apache-2.0. Verify terms on Hugging Face before commercial use.

Question 3

How do I run nishparadox/granite-guardian-3.2-5b-multi-harm-GGUF locally?

Accepted Answer

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Question 4

How much VRAM or disk space does nishparadox/granite-guardian-3.2-5b-multi-harm-GGUF need?

Accepted Answer

Runs locally from ~10.77 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).

nishparadox/granite-guardian-3.2-5b-multi-harm-GGUF overview

Repository Files & Downloads

Model Details

Model README

Granite Guardian 3.2 5B Multi-Harm F16 GGUF

Usage

Ollama

llama.cpp

Prompt Format for Multi-Risk Detection

Run nishparadox/granite-guardian-3.2-5b-multi-harm-GGUF with guIDE

Model ID	nishparadox/granite-guardian-3.2-5b-multi-harm-GGUF
Author	nishparadox
Pipeline	—
License	apache-2.0
Base model	ibm-granite/granite-guardian-3.2-5b
Last modified	2026-07-18T00:55:57.000Z