metadata
license: other
license_name: nvidia-open-model-license
license_link: >-
https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
library_name: transformers
pipeline_tag: text-generation
language:
- en
tags:
- nvidia
- llama-3
- pytorch
- TensorBlock
- GGUF
base_model: nvidia/Minitron-4B-Base
nvidia/Minitron-4B-Base - GGUF
This repo contains GGUF format model files for nvidia/Minitron-4B-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 |
|---|---|---|---|
| Minitron-4B-Base-Q2_K.gguf | Q2_K | 1.903 GB | smallest, significant quality loss - not recommended for most purposes |
| Minitron-4B-Base-Q3_K_S.gguf | Q3_K_S | 2.116 GB | very small, high quality loss |
| Minitron-4B-Base-Q3_K_M.gguf | Q3_K_M | 2.297 GB | very small, high quality loss |
| Minitron-4B-Base-Q3_K_L.gguf | Q3_K_L | 2.453 GB | small, substantial quality loss |
| Minitron-4B-Base-Q4_0.gguf | Q4_0 | 2.568 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Minitron-4B-Base-Q4_K_S.gguf | Q4_K_S | 2.583 GB | small, greater quality loss |
| Minitron-4B-Base-Q4_K_M.gguf | Q4_K_M | 2.697 GB | medium, balanced quality - recommended |
| Minitron-4B-Base-Q5_0.gguf | Q5_0 | 2.993 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Minitron-4B-Base-Q5_K_S.gguf | Q5_K_S | 2.993 GB | large, low quality loss - recommended |
| Minitron-4B-Base-Q5_K_M.gguf | Q5_K_M | 3.060 GB | large, very low quality loss - recommended |
| Minitron-4B-Base-Q6_K.gguf | Q6_K | 3.445 GB | very large, extremely low quality loss |
| Minitron-4B-Base-Q8_0.gguf | Q8_0 | 4.460 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_Minitron-4B-Base-GGUF --include "Minitron-4B-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_Minitron-4B-Base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'