Edit model card
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

ibm-granite/granite-8b-code-base-4k - GGUF

This repo contains GGUF format model files for ibm-granite/granite-8b-code-base-4k.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template


Model file specification

Filename Quant type File Size Description
granite-8b-code-base-4k-Q2_K.gguf Q2_K 2.852 GB smallest, significant quality loss - not recommended for most purposes
granite-8b-code-base-4k-Q3_K_S.gguf Q3_K_S 3.304 GB very small, high quality loss
granite-8b-code-base-4k-Q3_K_M.gguf Q3_K_M 3.674 GB very small, high quality loss
granite-8b-code-base-4k-Q3_K_L.gguf Q3_K_L 3.993 GB small, substantial quality loss
granite-8b-code-base-4k-Q4_0.gguf Q4_0 4.276 GB legacy; small, very high quality loss - prefer using Q3_K_M
granite-8b-code-base-4k-Q4_K_S.gguf Q4_K_S 4.305 GB small, greater quality loss
granite-8b-code-base-4k-Q4_K_M.gguf Q4_K_M 4.548 GB medium, balanced quality - recommended
granite-8b-code-base-4k-Q5_0.gguf Q5_0 5.190 GB legacy; medium, balanced quality - prefer using Q4_K_M
granite-8b-code-base-4k-Q5_K_S.gguf Q5_K_S 5.190 GB large, low quality loss - recommended
granite-8b-code-base-4k-Q5_K_M.gguf Q5_K_M 5.330 GB large, very low quality loss - recommended
granite-8b-code-base-4k-Q6_K.gguf Q6_K 6.161 GB very large, extremely low quality loss
granite-8b-code-base-4k-Q8_0.gguf Q8_0 7.977 GB very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/granite-8b-code-base-4k-GGUF --include "granite-8b-code-base-4k-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/granite-8b-code-base-4k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
0
GGUF
Model size
8.05B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Inference API (serverless) has been turned off for this model.

Model tree for tensorblock/granite-8b-code-base-4k-GGUF

Quantized
(22)
this model

Datasets used to train tensorblock/granite-8b-code-base-4k-GGUF

Evaluation results