OpenMath2-Llama3.1-70B-GGUF

tensorblock/OpenMath2-Llama3.1-70B-GGUF

OpenMath2-Llama3.1-70B-GGUF is a machine learning model from tensorblock. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as llama3.1.

<div style="width: auto; margin-left: auto; margin-right: auto" <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;" </div

Downloads · 30 days

140

7% of all-time downloads

All-time downloads

Public

Repo size

532 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.gguf26.4 GB · 100%

At a glance

Library: transformers
License: llama3.1
Access: Public
Created: Jan 24, 2025
Updated: Jan 27, 2026
SHA: 6302eb44

Base models

nvidia/OpenMath2-Llama3.1-70B

Datasets

nvidia/OpenMathInstruct-2

Model card

From the Hugging Face model README

nvidia/OpenMath2-Llama3.1-70B - GGUF

This repo contains GGUF format model files for nvidia/OpenMath2-Llama3.1-70B.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit ec7f3ac.

Our projects

<table border="1" cellspacing="0" cellpadding="10"> <tr> <th colspan="2" style="font-size: 25px;">Forge</th> </tr> <tr> <th colspan="2"> <img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/> </th> </tr> <tr> <th colspan="2">An OpenAI-compatible multi-provider routing layer.</th> </tr> <tr> <th colspan="2"> <a href="https://github.com/TensorBlock/forge" target="_blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">🚀 Try it now! 🚀</a> </th> </tr> <tr> <th style="font-size: 25px;">Awesome MCP Servers</th> <th style="font-size: 25px;">TensorBlock Studio</th> </tr> <tr> <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th> <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th> </tr> <tr> <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th> <th>A lightweight, open, and extensible multi-LLM interaction studio.</th> </tr> <tr> <th> <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">👀 See what we built 👀</a> </th> <th> <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">👀 See what we built 👀</a> </th> </tr> </table> ## Prompt template

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Model file specification

Filename	Quant type	File Size	Description
OpenMath2-Llama3.1-70B-Q2_K.gguf	Q2_K	26.375 GB	smallest, significant quality loss - not recommended for most purposes
OpenMath2-Llama3.1-70B-Q3_K_S.gguf	Q3_K_S	30.912 GB	very small, high quality loss
OpenMath2-Llama3.1-70B-Q3_K_M.gguf	Q3_K_M	34.267 GB	very small, high quality loss
OpenMath2-Llama3.1-70B-Q3_K_L.gguf	Q3_K_L	37.141 GB	small, substantial quality loss
OpenMath2-Llama3.1-70B-Q4_0.gguf	Q4_0	39.970 GB	legacy; small, very high quality loss - prefer using Q3_K_M
OpenMath2-Llama3.1-70B-Q4_K_S.gguf	Q4_K_S	40.347 GB	small, greater quality loss
OpenMath2-Llama3.1-70B-Q4_K_M.gguf	Q4_K_M	42.520 GB	medium, balanced quality - recommended
OpenMath2-Llama3.1-70B-Q5_0.gguf	Q5_0	48.657 GB	legacy; medium, balanced quality - prefer using Q4_K_M
OpenMath2-Llama3.1-70B-Q5_K_S.gguf	Q5_K_S	48.657 GB	large, low quality loss - recommended
OpenMath2-Llama3.1-70B-Q5_K_M.gguf	Q5_K_M	49.950 GB	large, very low quality loss - recommended
OpenMath2-Llama3.1-70B-Q6_K	Q6_K	57.888 GB	very large, extremely low quality loss
OpenMath2-Llama3.1-70B-Q8_0	Q8_0	74.975 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/OpenMath2-Llama3.1-70B-GGUF --include "OpenMath2-Llama3.1-70B-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/OpenMath2-Llama3.1-70B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'

Library: transformers
License: llama3.1
Languages: en
Created: Jan 24, 2025
Updated: Jan 27, 2026