π Model Description
license: apache-2.0 library_name: transformers tags:
- language
- granite-4.0
- gguf
- ibm-granite/granite-4.0-h-small
Granite 4.0 H-Small (GGUF)
>[!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-4.0-h-small
π GGUF File List
| π Filename | π¦ Size | β‘ Download |
|---|---|---|
|
granite-4.0-h-small-Q2_K.gguf
LFS
Q2
|
10.97 GB | Download |
|
granite-4.0-h-small-Q3_K_L.gguf
LFS
Q3
|
15.34 GB | Download |
|
granite-4.0-h-small-Q3_K_M.gguf
LFS
Q3
|
14.31 GB | Download |
|
granite-4.0-h-small-Q3_K_S.gguf
LFS
Q3
|
13.09 GB | Download |
|
granite-4.0-h-small-Q4_0.gguf
Recommended
LFS
Q4
|
17.02 GB | Download |
|
granite-4.0-h-small-Q4_1.gguf
LFS
Q4
|
18.87 GB | Download |
|
granite-4.0-h-small-Q4_K_M.gguf
LFS
Q4
|
18.14 GB | Download |
|
granite-4.0-h-small-Q4_K_S.gguf
LFS
Q4
|
17.16 GB | Download |
|
granite-4.0-h-small-Q5_0.gguf
LFS
Q5
|
20.72 GB | Download |
|
granite-4.0-h-small-Q5_1.gguf
LFS
Q5
|
22.57 GB | Download |
|
granite-4.0-h-small-Q5_K_M.gguf
LFS
Q5
|
21.3 GB | Download |
|
granite-4.0-h-small-Q5_K_S.gguf
LFS
Q5
|
20.72 GB | Download |
|
granite-4.0-h-small-Q6_K.gguf
LFS
Q6
|
24.65 GB | Download |
|
granite-4.0-h-small-Q8_0.gguf
LFS
Q8
|
31.91 GB | Download |
|
granite-4.0-h-small-f16.gguf
LFS
FP16
|
60.02 GB | Download |