tensorblock/nvidia_Llama-3.1-Minitron-4B-Depth-Base-GGUF

nvidia/Llama-3.1-Minitron-4B-Depth-Base - GGUF

This repo contains GGUF format model files for nvidia/Llama-3.1-Minitron-4B-Depth-Base.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5165.

Our projects

Forge
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

Prompt template

Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.

Model file specification

Filename	Quant type	File Size	Description
Llama-3.1-Minitron-4B-Depth-Base-Q2_K.gguf	Q2_K	1.895 GB	smallest, significant quality loss - not recommended for most purposes
Llama-3.1-Minitron-4B-Depth-Base-Q3_K_S.gguf	Q3_K_S	2.165 GB	very small, high quality loss
Llama-3.1-Minitron-4B-Depth-Base-Q3_K_M.gguf	Q3_K_M	2.342 GB	very small, high quality loss
Llama-3.1-Minitron-4B-Depth-Base-Q3_K_L.gguf	Q3_K_L	2.493 GB	small, substantial quality loss
Llama-3.1-Minitron-4B-Depth-Base-Q4_0.gguf	Q4_0	2.698 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Llama-3.1-Minitron-4B-Depth-Base-Q4_K_S.gguf	Q4_K_S	2.715 GB	small, greater quality loss
Llama-3.1-Minitron-4B-Depth-Base-Q4_K_M.gguf	Q4_K_M	2.828 GB	medium, balanced quality - recommended
Llama-3.1-Minitron-4B-Depth-Base-Q5_0.gguf	Q5_0	3.200 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Llama-3.1-Minitron-4B-Depth-Base-Q5_K_S.gguf	Q5_K_S	3.200 GB	large, low quality loss - recommended
Llama-3.1-Minitron-4B-Depth-Base-Q5_K_M.gguf	Q5_K_M	3.266 GB	large, very low quality loss - recommended
Llama-3.1-Minitron-4B-Depth-Base-Q6_K.gguf	Q6_K	3.733 GB	very large, extremely low quality loss
Llama-3.1-Minitron-4B-Depth-Base-Q8_0.gguf	Q8_0	4.832 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/nvidia_Llama-3.1-Minitron-4B-Depth-Base-GGUF --include "Llama-3.1-Minitron-4B-Depth-Base-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/nvidia_Llama-3.1-Minitron-4B-Depth-Base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'