Rombo Org Rombo LLM V3.1 QWQ 32b GGUF

🚀 Llamacpp imatrix Quantizations of Rombo-LLM-V3.1-QWQ-32b by Rombo-Org

This project provides llama.cpp imatrix quantizations of the Rombo-LLM-V3.1-QWQ-32b model, enabling efficient deployment and use.

🚀 Quick Start

• Run in LM Studio: You can directly run these quantized models in LM Studio.
• Run with llama.cpp: Use llama.cpp or any other llama.cpp - based project to run the models.

✨ Features

• High - Quality Quantization: Using llama.cpp release b4792 for quantization to ensure high - quality model performance.
• Multiple Quant Types: Provide a variety of quant types to meet different performance and quality requirements.
• Online Repacking: Support online repacking for weights to improve performance on ARM and AVX machines.

📦 Installation

Downloading using huggingface - cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/Rombo-Org_Rombo-LLM-V3.1-QWQ-32b-GGUF --include "Rombo-Org_Rombo-LLM-V3.1-QWQ-32b-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/Rombo-Org_Rombo-LLM-V3.1-QWQ-32b-GGUF --include "Rombo-Org_Rombo-LLM-V3.1-QWQ-32b-Q8_0/*" --local-dir ./

💻 Usage Examples

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
<think>

📚 Documentation

Download a file (not the whole branch) from below:

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

Benchmarks on an AVX2 system (EPYC7702)

📄 License

This project is licensed under the Apache - 2.0 license.

Acknowledgments

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