Hugging Face's logo

tensorblock
/
EXAONE-3.5-32B-Instruct-GGUF

Text Generation
Transformers
GGUF
English
Korean
lg-ai
exaone
exaone-3.5
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
EXAONE-3.5-32B-Instruct-GGUF / README.md
morriszms's picture
morriszms
Upload folder using huggingface_hub
8196d31 verified
preview code
|
raw
history blame contribute delete
5.14 kB
metadata
license: other
license_name: exaone
license_link: LICENSE
language:
  - en
  - ko
tags:
  - lg-ai
  - exaone
  - exaone-3.5
  - TensorBlock
  - GGUF
pipeline_tag: text-generation
library_name: transformers
base_model: LGAI-EXAONE/EXAONE-3.5-32B-Instruct
TensorBlock

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

LGAI-EXAONE/EXAONE-3.5-32B-Instruct - GGUF

This repo contains GGUF format model files for LGAI-EXAONE/EXAONE-3.5-32B-Instruct.

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

Prompt template 

[|system|]{system_prompt}[|endofturn|]
[|user|]{prompt}
[|assistant|]

Model file specification

Filename Quant type File Size Description
EXAONE-3.5-32B-Instruct-Q2_K.gguf Q2_K 11.926 GB smallest, significant quality loss - not recommended for most purposes
EXAONE-3.5-32B-Instruct-Q3_K_S.gguf Q3_K_S 13.963 GB very small, high quality loss
EXAONE-3.5-32B-Instruct-Q3_K_M.gguf Q3_K_M 15.494 GB very small, high quality loss
EXAONE-3.5-32B-Instruct-Q3_K_L.gguf Q3_K_L 16.796 GB small, substantial quality loss
EXAONE-3.5-32B-Instruct-Q4_0.gguf Q4_0 18.143 GB legacy; small, very high quality loss - prefer using Q3_K_M
EXAONE-3.5-32B-Instruct-Q4_K_S.gguf Q4_K_S 18.286 GB small, greater quality loss
EXAONE-3.5-32B-Instruct-Q4_K_M.gguf Q4_K_M 19.344 GB medium, balanced quality - recommended
EXAONE-3.5-32B-Instruct-Q5_0.gguf Q5_0 22.078 GB legacy; medium, balanced quality - prefer using Q4_K_M
EXAONE-3.5-32B-Instruct-Q5_K_S.gguf Q5_K_S 22.078 GB large, low quality loss - recommended
EXAONE-3.5-32B-Instruct-Q5_K_M.gguf Q5_K_M 22.697 GB large, very low quality loss - recommended
EXAONE-3.5-32B-Instruct-Q6_K.gguf Q6_K 26.259 GB very large, extremely low quality loss
EXAONE-3.5-32B-Instruct-Q8_0.gguf Q8_0 34.010 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/EXAONE-3.5-32B-Instruct-GGUF --include "EXAONE-3.5-32B-Instruct-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/EXAONE-3.5-32B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'