TensorBlock

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

OpenBuddy/openbuddy-mixtral-8x7b-v15.4 - GGUF

This repo contains GGUF format model files for OpenBuddy/openbuddy-mixtral-8x7b-v15.4.

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-mixtral-8x7b-v15.4-Q2_K.gguf Q2_K 17.333 GB smallest, significant quality loss - not recommended for most purposes
openbuddy-mixtral-8x7b-v15.4-Q3_K_S.gguf Q3_K_S 20.456 GB very small, high quality loss
openbuddy-mixtral-8x7b-v15.4-Q3_K_M.gguf Q3_K_M 22.570 GB very small, high quality loss
openbuddy-mixtral-8x7b-v15.4-Q3_K_L.gguf Q3_K_L 24.193 GB small, substantial quality loss
openbuddy-mixtral-8x7b-v15.4-Q4_0.gguf Q4_0 26.470 GB legacy; small, very high quality loss - prefer using Q3_K_M
openbuddy-mixtral-8x7b-v15.4-Q4_K_S.gguf Q4_K_S 26.772 GB small, greater quality loss
openbuddy-mixtral-8x7b-v15.4-Q4_K_M.gguf Q4_K_M 28.475 GB medium, balanced quality - recommended
openbuddy-mixtral-8x7b-v15.4-Q5_0.gguf Q5_0 32.260 GB legacy; medium, balanced quality - prefer using Q4_K_M
openbuddy-mixtral-8x7b-v15.4-Q5_K_S.gguf Q5_K_S 32.260 GB large, low quality loss - recommended
openbuddy-mixtral-8x7b-v15.4-Q5_K_M.gguf Q5_K_M 33.258 GB large, very low quality loss - recommended
openbuddy-mixtral-8x7b-v15.4-Q6_K.gguf Q6_K 38.412 GB very large, extremely low quality loss
openbuddy-mixtral-8x7b-v15.4-Q8_0.gguf Q8_0 49.667 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-mixtral-8x7b-v15.4-GGUF --include "openbuddy-mixtral-8x7b-v15.4-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-mixtral-8x7b-v15.4-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
235
GGUF
Model size
46.7B 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-mixtral-8x7b-v15.4-GGUF

Quantized
(4)
this model