TensorBlock

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

ChenWeiLi/MedLlama-3-8B_DARE - GGUF

This repo contains GGUF format model files for ChenWeiLi/MedLlama-3-8B_DARE.

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
MedLlama-3-8B_DARE-Q2_K.gguf Q2_K 2.961 GB smallest, significant quality loss - not recommended for most purposes
MedLlama-3-8B_DARE-Q3_K_S.gguf Q3_K_S 3.413 GB very small, high quality loss
MedLlama-3-8B_DARE-Q3_K_M.gguf Q3_K_M 3.743 GB very small, high quality loss
MedLlama-3-8B_DARE-Q3_K_L.gguf Q3_K_L 4.025 GB small, substantial quality loss
MedLlama-3-8B_DARE-Q4_0.gguf Q4_0 4.341 GB legacy; small, very high quality loss - prefer using Q3_K_M
MedLlama-3-8B_DARE-Q4_K_S.gguf Q4_K_S 4.370 GB small, greater quality loss
MedLlama-3-8B_DARE-Q4_K_M.gguf Q4_K_M 4.583 GB medium, balanced quality - recommended
MedLlama-3-8B_DARE-Q5_0.gguf Q5_0 5.215 GB legacy; medium, balanced quality - prefer using Q4_K_M
MedLlama-3-8B_DARE-Q5_K_S.gguf Q5_K_S 5.215 GB large, low quality loss - recommended
MedLlama-3-8B_DARE-Q5_K_M.gguf Q5_K_M 5.339 GB large, very low quality loss - recommended
MedLlama-3-8B_DARE-Q6_K.gguf Q6_K 6.143 GB very large, extremely low quality loss
MedLlama-3-8B_DARE-Q8_0.gguf Q8_0 7.954 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/MedLlama-3-8B_DARE-GGUF --include "MedLlama-3-8B_DARE-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/MedLlama-3-8B_DARE-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
328
GGUF
Model size
8.03B 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/MedLlama-3-8B_DARE-GGUF

Quantized
(3)
this model