tensorblock/granite-20b-code-base-8k-GGUF

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

ibm-granite/granite-20b-code-base-8k - GGUF

This repo contains GGUF format model files for ibm-granite/granite-20b-code-base-8k.

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

Run them on the TensorBlock client using your local machine ↗

Prompt template

Model file specification

Filename	Quant type	File Size	Description
granite-20b-code-base-8k-Q2_K.gguf	Q2_K	7.385 GB	smallest, significant quality loss - not recommended for most purposes
granite-20b-code-base-8k-Q3_K_S.gguf	Q3_K_S	8.321 GB	very small, high quality loss
granite-20b-code-base-8k-Q3_K_M.gguf	Q3_K_M	9.841 GB	very small, high quality loss
granite-20b-code-base-8k-Q3_K_L.gguf	Q3_K_L	10.930 GB	small, substantial quality loss
granite-20b-code-base-8k-Q4_0.gguf	Q4_0	10.759 GB	legacy; small, very high quality loss - prefer using Q3_K_M
granite-20b-code-base-8k-Q4_K_S.gguf	Q4_K_S	10.865 GB	small, greater quality loss
granite-20b-code-base-8k-Q4_K_M.gguf	Q4_K_M	11.940 GB	medium, balanced quality - recommended
granite-20b-code-base-8k-Q5_0.gguf	Q5_0	13.054 GB	legacy; medium, balanced quality - prefer using Q4_K_M
granite-20b-code-base-8k-Q5_K_S.gguf	Q5_K_S	13.054 GB	large, low quality loss - recommended
granite-20b-code-base-8k-Q5_K_M.gguf	Q5_K_M	13.792 GB	large, very low quality loss - recommended
granite-20b-code-base-8k-Q6_K.gguf	Q6_K	15.492 GB	very large, extremely low quality loss
granite-20b-code-base-8k-Q8_0.gguf	Q8_0	20.006 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-20b-code-base-8k-GGUF --include "granite-20b-code-base-8k-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-20b-code-base-8k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'