tensorblock/deepseek-coder-6.7b-base-GGUF

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

deepseek-ai/deepseek-coder-6.7b-base - GGUF

This repo contains GGUF format model files for deepseek-ai/deepseek-coder-6.7b-base.

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
deepseek-coder-6.7b-base-Q2_K.gguf	Q2_K	2.360 GB	smallest, significant quality loss - not recommended for most purposes
deepseek-coder-6.7b-base-Q3_K_S.gguf	Q3_K_S	2.747 GB	very small, high quality loss
deepseek-coder-6.7b-base-Q3_K_M.gguf	Q3_K_M	3.073 GB	very small, high quality loss
deepseek-coder-6.7b-base-Q3_K_L.gguf	Q3_K_L	3.352 GB	small, substantial quality loss
deepseek-coder-6.7b-base-Q4_0.gguf	Q4_0	3.565 GB	legacy; small, very high quality loss - prefer using Q3_K_M
deepseek-coder-6.7b-base-Q4_K_S.gguf	Q4_K_S	3.594 GB	small, greater quality loss
deepseek-coder-6.7b-base-Q4_K_M.gguf	Q4_K_M	3.802 GB	medium, balanced quality - recommended
deepseek-coder-6.7b-base-Q5_0.gguf	Q5_0	4.334 GB	legacy; medium, balanced quality - prefer using Q4_K_M
deepseek-coder-6.7b-base-Q5_K_S.gguf	Q5_K_S	4.334 GB	large, low quality loss - recommended
deepseek-coder-6.7b-base-Q5_K_M.gguf	Q5_K_M	4.457 GB	large, very low quality loss - recommended
deepseek-coder-6.7b-base-Q6_K.gguf	Q6_K	5.151 GB	very large, extremely low quality loss
deepseek-coder-6.7b-base-Q8_0.gguf	Q8_0	6.672 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/deepseek-coder-6.7b-base-GGUF --include "deepseek-coder-6.7b-base-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/deepseek-coder-6.7b-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'