Q: What is lm-kit/granite-3.3-8b-instruct-gguf?

--- license: apache-2.0 --- --- license: apache-2.0 --- ## Model Summary This repository hosts quantized versions of the IBM Granite 3.3 8B Instruct model. **Format:** GGUF **Converter:** llama.cpp 12b17501e6015ffe568ac54fdf08e6580833bf1b **Quantizer:** LM-Kit.NET 2025.4.9 For more detailed information on the base model, please visit the following link: - [granite-3.3-8b-instruct](https://huggingface.co/ibm-granite/granite-3.3-8b-instruct)

Question 1

What is lm-kit/granite-3.3-8b-instruct-gguf?

Accepted Answer

---

license: apache-2.0

---

license: apache-2.0

---

Model Summary

This repository hosts quantized versions of the IBM Granite 3.3 8B Instruct model.

Format: GGUF

Converter: llama.cpp 12b17501e6015ffe568ac54fdf08e6580833bf1b

Quantizer: LM-Kit.NET 2025.4.9

For more detailed information on the base model, please visit the following link:

granite-3.3-8b-instruct

Question 2

What license applies to lm-kit/granite-3.3-8b-instruct-gguf?

Accepted Answer

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

Question 3

How do I run lm-kit/granite-3.3-8b-instruct-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 lm-kit/granite-3.3-8b-instruct-gguf need?

Accepted Answer

Runs locally from ~4.60 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

File	Type	Quantization	Size	Link
granite-3.3-8B-Instruct-F16.gguf	GGUF	F16	15.22 GB	Download
granite-3.3-8B-Instruct-Q4_K_M.gguf	GGUF	Q4_K_M	4.60 GB	Download

Model ID	lm-kit/granite-3.3-8b-instruct-gguf
Author	lm-kit
Pipeline	—
License	apache-2.0
Base model	—
Last modified	2026-08-11T20:06:10.000Z

lm-kit/granite-3.3-8b-instruct-gguf overview

Repository Files & Downloads

Model Details

Model README

Model Summary

Run lm-kit/granite-3.3-8b-instruct-gguf with guIDE