Openbuddy OpenBuddy R1 0528 Distill Qwen3 32B Preview0 QAT GGUF

🚀 Llamacpp imatrix Quantizations of OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT by OpenBuddy

This project provides Llama.cpp imatrix quantizations of the OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT model, enabling efficient deployment and inference across various hardware platforms.

🚀 Quick Start

Running the Model

• Using LM Studio: You can run the quantized models in LM Studio.
• Using llama.cpp: Run the models directly with llama.cpp, or any other llama.cpp based project.

Prompt Format

<|role|>system<|says|>{system_prompt}<|end|>
<|role|>user<|says|>{prompt}<|end|>
<|role|>assistant<|says|>

✨ Features

• Multiple Quantization Types: Offers a wide range of quantization types, including BF16, Q8_0, Q6_K_L, etc., to meet different performance and quality requirements.
• Online Repacking: Supports online repacking of weights for ARM and AVX machines, improving performance.
• Multilingual Support: The original model supports multiple languages, including Chinese, English, French, German, Japanese, Korean, Italian, and Finnish.

📦 Installation

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/OpenBuddy_OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT-GGUF --include "OpenBuddy_OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/OpenBuddy_OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT-GGUF --include "OpenBuddy_OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT-Q8_0/*" --local-dir ./

You can either specify a new local-dir (OpenBuddy_OpenBuddy-R1-0528-Distill-Qwen3-32B-Preview0-QAT-Q8_0) or download them all in place (./)

📚 Documentation

Model Information

Download Options

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

ARM/AVX information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.

Which file should I choose?

🔧 Technical Details

Quantization Process

The quantizations are performed using llama.cpp release b5627. All quants are made using the imatrix option with a dataset from here.

Online Repacking

The concept of "online repacking" for weights is introduced, which can automatically optimize the weights for ARM and AVX machines on the fly. Details can be found in this PR.

📄 License

This project is licensed under the Apache-2.0 license.

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Thank you to LM Studio for sponsoring my work.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski