Edit model card
TensorBlock

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

Locutusque/Hercules-3.1-Mistral-7B - GGUF

This repo contains GGUF format model files for Locutusque/Hercules-3.1-Mistral-7B.

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
Hercules-3.1-Mistral-7B-Q2_K.gguf Q2_K 2.532 GB smallest, significant quality loss - not recommended for most purposes
Hercules-3.1-Mistral-7B-Q3_K_S.gguf Q3_K_S 2.947 GB very small, high quality loss
Hercules-3.1-Mistral-7B-Q3_K_M.gguf Q3_K_M 3.277 GB very small, high quality loss
Hercules-3.1-Mistral-7B-Q3_K_L.gguf Q3_K_L 3.560 GB small, substantial quality loss
Hercules-3.1-Mistral-7B-Q4_0.gguf Q4_0 3.827 GB legacy; small, very high quality loss - prefer using Q3_K_M
Hercules-3.1-Mistral-7B-Q4_K_S.gguf Q4_K_S 3.856 GB small, greater quality loss
Hercules-3.1-Mistral-7B-Q4_K_M.gguf Q4_K_M 4.068 GB medium, balanced quality - recommended
Hercules-3.1-Mistral-7B-Q5_0.gguf Q5_0 4.654 GB legacy; medium, balanced quality - prefer using Q4_K_M
Hercules-3.1-Mistral-7B-Q5_K_S.gguf Q5_K_S 4.654 GB large, low quality loss - recommended
Hercules-3.1-Mistral-7B-Q5_K_M.gguf Q5_K_M 4.779 GB large, very low quality loss - recommended
Hercules-3.1-Mistral-7B-Q6_K.gguf Q6_K 5.534 GB very large, extremely low quality loss
Hercules-3.1-Mistral-7B-Q8_0.gguf Q8_0 7.167 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/Hercules-3.1-Mistral-7B-GGUF --include "Hercules-3.1-Mistral-7B-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/Hercules-3.1-Mistral-7B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
133
GGUF
Model size
7.24B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for tensorblock/Hercules-3.1-Mistral-7B-GGUF

Quantized
(6)
this model

Dataset used to train tensorblock/Hercules-3.1-Mistral-7B-GGUF

Evaluation results