TensorBlock

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

SJ-Donald/llama3-passthrough - GGUF

This repo contains GGUF format model files for SJ-Donald/llama3-passthrough.

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
llama3-passthrough-Q2_K.gguf Q2_K 4.157 GB smallest, significant quality loss - not recommended for most purposes
llama3-passthrough-Q3_K_S.gguf Q3_K_S 4.810 GB very small, high quality loss
llama3-passthrough-Q3_K_M.gguf Q3_K_M 5.304 GB very small, high quality loss
llama3-passthrough-Q3_K_L.gguf Q3_K_L 5.728 GB small, substantial quality loss
llama3-passthrough-Q4_0.gguf Q4_0 6.170 GB legacy; small, very high quality loss - prefer using Q3_K_M
llama3-passthrough-Q4_K_S.gguf Q4_K_S 6.213 GB small, greater quality loss
llama3-passthrough-Q4_K_M.gguf Q4_K_M 6.532 GB medium, balanced quality - recommended
llama3-passthrough-Q5_0.gguf Q5_0 7.450 GB legacy; medium, balanced quality - prefer using Q4_K_M
llama3-passthrough-Q5_K_S.gguf Q5_K_S 7.450 GB large, low quality loss - recommended
llama3-passthrough-Q5_K_M.gguf Q5_K_M 7.636 GB large, very low quality loss - recommended
llama3-passthrough-Q6_K.gguf Q6_K 8.810 GB very large, extremely low quality loss
llama3-passthrough-Q8_0.gguf Q8_0 11.408 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/llama3-passthrough-GGUF --include "llama3-passthrough-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/llama3-passthrough-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
34
GGUF
Model size
11.5B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/llama3-passthrough-GGUF

Quantized
(1)
this model