π Model Description
pipeline_tag: text-generation inference: false license: apache-2.0 library_name: transformers tags:
- language
- granite-3.3
- gguf
- ibm-granite/granite-3.3-8b-instruct
>[!NOTE]
This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite base model.
Please reference the base model's full model card here:
https://huggingface.co/ibm-granite/granite-3.3-8b-instruct
π GGUF File List
| π Filename | π¦ Size | β‘ Download |
|---|---|---|
|
granite-3.3-8b-instruct-Q2_K.gguf
LFS
Q2
|
2.89 GB | Download |
|
granite-3.3-8b-instruct-Q3_K_L.gguf
LFS
Q3
|
4.05 GB | Download |
|
granite-3.3-8b-instruct-Q3_K_M.gguf
LFS
Q3
|
3.72 GB | Download |
|
granite-3.3-8b-instruct-Q3_K_S.gguf
LFS
Q3
|
3.35 GB | Download |
|
granite-3.3-8b-instruct-Q4_0.gguf
Recommended
LFS
Q4
|
4.33 GB | Download |
|
granite-3.3-8b-instruct-Q4_1.gguf
LFS
Q4
|
4.8 GB | Download |
|
granite-3.3-8b-instruct-Q4_K_M.gguf
LFS
Q4
|
4.6 GB | Download |
|
granite-3.3-8b-instruct-Q4_K_S.gguf
LFS
Q4
|
4.36 GB | Download |
|
granite-3.3-8b-instruct-Q5_0.gguf
LFS
Q5
|
5.26 GB | Download |
|
granite-3.3-8b-instruct-Q5_1.gguf
LFS
Q5
|
5.72 GB | Download |
|
granite-3.3-8b-instruct-Q5_K_M.gguf
LFS
Q5
|
5.4 GB | Download |
|
granite-3.3-8b-instruct-Q5_K_S.gguf
LFS
Q5
|
5.26 GB | Download |
|
granite-3.3-8b-instruct-Q6_K.gguf
LFS
Q6
|
6.24 GB | Download |
|
granite-3.3-8b-instruct-Q8_0.gguf
LFS
Q8
|
8.09 GB | Download |
|
granite-3.3-8b-instruct-f16.gguf
LFS
FP16
|
15.22 GB | Download |