TensorBlock

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

furiosa-ai/EXAONE-3.0-7.8B-Instruct-converted - GGUF

This repo contains GGUF format model files for furiosa-ai/EXAONE-3.0-7.8B-Instruct-converted.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template

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

Model file specification

Filename Quant type File Size Description
EXAONE-3.0-7.8B-Instruct-converted-Q2_K.gguf Q2_K 3.054 GB smallest, significant quality loss - not recommended for most purposes
EXAONE-3.0-7.8B-Instruct-converted-Q3_K_S.gguf Q3_K_S 3.528 GB very small, high quality loss
EXAONE-3.0-7.8B-Instruct-converted-Q3_K_M.gguf Q3_K_M 3.883 GB very small, high quality loss
EXAONE-3.0-7.8B-Instruct-converted-Q3_K_L.gguf Q3_K_L 4.186 GB small, substantial quality loss
EXAONE-3.0-7.8B-Instruct-converted-Q4_0.gguf Q4_0 4.511 GB legacy; small, very high quality loss - prefer using Q3_K_M
EXAONE-3.0-7.8B-Instruct-converted-Q4_K_S.gguf Q4_K_S 4.543 GB small, greater quality loss
EXAONE-3.0-7.8B-Instruct-converted-Q4_K_M.gguf Q4_K_M 4.771 GB medium, balanced quality - recommended
EXAONE-3.0-7.8B-Instruct-converted-Q5_0.gguf Q5_0 5.436 GB legacy; medium, balanced quality - prefer using Q4_K_M
EXAONE-3.0-7.8B-Instruct-converted-Q5_K_S.gguf Q5_K_S 5.436 GB large, low quality loss - recommended
EXAONE-3.0-7.8B-Instruct-converted-Q5_K_M.gguf Q5_K_M 5.570 GB large, very low quality loss - recommended
EXAONE-3.0-7.8B-Instruct-converted-Q6_K.gguf Q6_K 6.419 GB very large, extremely low quality loss
EXAONE-3.0-7.8B-Instruct-converted-Q8_0.gguf Q8_0 8.312 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-3.0-7.8B-Instruct-converted-GGUF --include "EXAONE-3.0-7.8B-Instruct-converted-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-3.0-7.8B-Instruct-converted-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
146
GGUF
Model size
7.82B 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/EXAONE-3.0-7.8B-Instruct-converted-GGUF

Quantized
(1)
this model