metadata
license: other
license_name: nvidia-open-model-license-agreement
license_link: >-
https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
library_name: transformers
base_model: nvidia/Riva-Translate-4B-Instruct
tags:
- TensorBlock
- GGUF
nvidia/Riva-Translate-4B-Instruct - GGUF
This repo contains GGUF format model files for nvidia/Riva-Translate-4B-Instruct.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.
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
<s>System
You are a translation expert.</s>
<s>User
{prompt}</s>
<s>Assistant
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Riva-Translate-4B-Instruct-Q2_K.gguf | Q2_K | 1.858 GB | smallest, significant quality loss - not recommended for most purposes |
| Riva-Translate-4B-Instruct-Q3_K_S.gguf | Q3_K_S | 2.082 GB | very small, high quality loss |
| Riva-Translate-4B-Instruct-Q3_K_M.gguf | Q3_K_M | 2.270 GB | very small, high quality loss |
| Riva-Translate-4B-Instruct-Q3_K_L.gguf | Q3_K_L | 2.389 GB | small, substantial quality loss |
| Riva-Translate-4B-Instruct-Q4_0.gguf | Q4_0 | 2.464 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Riva-Translate-4B-Instruct-Q4_K_S.gguf | Q4_K_S | 2.585 GB | small, greater quality loss |
| Riva-Translate-4B-Instruct-Q4_K_M.gguf | Q4_K_M | 2.759 GB | medium, balanced quality - recommended |
| Riva-Translate-4B-Instruct-Q5_0.gguf | Q5_0 | 2.936 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Riva-Translate-4B-Instruct-Q5_K_S.gguf | Q5_K_S | 2.992 GB | large, low quality loss - recommended |
| Riva-Translate-4B-Instruct-Q5_K_M.gguf | Q5_K_M | 3.140 GB | large, very low quality loss - recommended |
| Riva-Translate-4B-Instruct-Q6_K.gguf | Q6_K | 3.656 GB | very large, extremely low quality loss |
| Riva-Translate-4B-Instruct-Q8_0.gguf | Q8_0 | 4.449 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_Riva-Translate-4B-Instruct-GGUF --include "Riva-Translate-4B-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/nvidia_Riva-Translate-4B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'