TensorBlock

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

OpenBuddy/openbuddy-deepseek-67b-v15.2 - GGUF

This repo contains GGUF format model files for OpenBuddy/openbuddy-deepseek-67b-v15.2.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Prompt template


Model file specification

Filename Quant type File Size Description
openbuddy-deepseek-67b-v15.2-Q2_K.gguf Q2_K 25.121 GB smallest, significant quality loss - not recommended for most purposes
openbuddy-deepseek-67b-v15.2-Q3_K_S.gguf Q3_K_S 29.309 GB very small, high quality loss
openbuddy-deepseek-67b-v15.2-Q3_K_M.gguf Q3_K_M 32.652 GB very small, high quality loss
openbuddy-deepseek-67b-v15.2-Q3_K_L.gguf Q3_K_L 35.575 GB small, substantial quality loss
openbuddy-deepseek-67b-v15.2-Q4_0.gguf Q4_0 38.152 GB legacy; small, very high quality loss - prefer using Q3_K_M
openbuddy-deepseek-67b-v15.2-Q4_K_S.gguf Q4_K_S 38.404 GB small, greater quality loss
openbuddy-deepseek-67b-v15.2-Q4_K_M.gguf Q4_K_M 40.439 GB medium, balanced quality - recommended
openbuddy-deepseek-67b-v15.2-Q5_0.gguf Q5_0 46.475 GB legacy; medium, balanced quality - prefer using Q4_K_M
openbuddy-deepseek-67b-v15.2-Q5_K_S.gguf Q5_K_S 46.475 GB large, low quality loss - recommended
openbuddy-deepseek-67b-v15.2-Q5_K_M.gguf Q5_K_M 47.653 GB large, very low quality loss - recommended
openbuddy-deepseek-67b-v15.2-Q6_K Q6_K 55.319 GB very large, extremely low quality loss
openbuddy-deepseek-67b-v15.2-Q8_0 Q8_0 12.169 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/openbuddy-deepseek-67b-v15.2-GGUF --include "openbuddy-deepseek-67b-v15.2-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/openbuddy-deepseek-67b-v15.2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
188
GGUF
Model size
67.4B 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/openbuddy-deepseek-67b-v15.2-GGUF

Quantized
(1)
this model