Hugging Face's logo

tensorblock
/
Llamix2-MLewd-4x13B-GGUF

GGUF
Not-For-All-Audiences
nsfw
TensorBlock
GGUF
Inference Endpoints
Model card Files Community
Llamix2-MLewd-4x13B-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
710bdf4 verified
preview code
|
raw
history blame contribute delete
4.77 kB
metadata
license: cc-by-nc-4.0
tags:
  - not-for-all-audiences
  - nsfw
  - TensorBlock
  - GGUF
base_model: Undi95/Llamix2-MLewd-4x13B
TensorBlock

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

Undi95/Llamix2-MLewd-4x13B - GGUF

This repo contains GGUF format model files for Undi95/Llamix2-MLewd-4x13B.

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
Llamix2-MLewd-4x13B-Q2_K.gguf Q2_K 14.081 GB smallest, significant quality loss - not recommended for most purposes
Llamix2-MLewd-4x13B-Q3_K_S.gguf Q3_K_S 16.611 GB very small, high quality loss
Llamix2-MLewd-4x13B-Q3_K_M.gguf Q3_K_M 18.471 GB very small, high quality loss
Llamix2-MLewd-4x13B-Q3_K_L.gguf Q3_K_L 20.071 GB small, substantial quality loss
Llamix2-MLewd-4x13B-Q4_0.gguf Q4_0 21.702 GB legacy; small, very high quality loss - prefer using Q3_K_M
Llamix2-MLewd-4x13B-Q4_K_S.gguf Q4_K_S 21.892 GB small, greater quality loss
Llamix2-MLewd-4x13B-Q4_K_M.gguf Q4_K_M 23.297 GB medium, balanced quality - recommended
Llamix2-MLewd-4x13B-Q5_0.gguf Q5_0 26.493 GB legacy; medium, balanced quality - prefer using Q4_K_M
Llamix2-MLewd-4x13B-Q5_K_S.gguf Q5_K_S 26.493 GB large, low quality loss - recommended
Llamix2-MLewd-4x13B-Q5_K_M.gguf Q5_K_M 27.315 GB large, very low quality loss - recommended
Llamix2-MLewd-4x13B-Q6_K.gguf Q6_K 31.584 GB very large, extremely low quality loss
Llamix2-MLewd-4x13B-Q8_0.gguf Q8_0 40.908 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/Llamix2-MLewd-4x13B-GGUF --include "Llamix2-MLewd-4x13B-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/Llamix2-MLewd-4x13B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'