Allura Org Remnant Glm4 32b GGUF

🚀 Llamacpp imatrix Quantizations of remnant - glm4 - 32b by allura - org

This project provides quantized versions of the allura - org/remnant - glm4 - 32b model using llama.cpp. It offers various quantization types to balance between model quality and file size, suitable for different hardware and usage scenarios.

🚀 Quick Start

Running the Model

• You can run the quantized models in LM Studio.
• Or run them directly with llama.cpp, or any other llama.cpp - based project.

Prompt Format

[gMASK]<sop><|system|>
{system_prompt}<|user|>
{prompt}<|assistant|>

✨ Features

• Multiple Quantization Types: Offers a wide range of quantization types (e.g., bf16, Q8_0, Q6_K_L, etc.) to meet different requirements for quality and resource usage.
• Online Repacking: Some quantization types support online repacking of weights, which can improve performance on ARM and AVX machines.

📦 Installation

Prerequisites

First, make sure you have huggingface - cli installed:

pip install -U "huggingface_hub[cli]"

Downloading a Specific File

You can target the specific file you want:

huggingface - cli download bartowski/allura - org_remnant - glm4 - 32b - GGUF --include "allura - org_remnant - glm4 - 32b - Q4_K_M.gguf" --local - dir ./

Downloading Split Files

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

huggingface - cli download bartowski/allura - org_remnant - glm4 - 32b - GGUF --include "allura - org_remnant - glm4 - 32b - Q8_0/*" --local - dir ./

You can either specify a new local - dir (e.g., allura - org_remnant - glm4 - 32b - Q8_0) or download them all in place (./).

💻 Usage Examples

Downloading Files

# Download a specific file
huggingface - cli download bartowski/allura - org_remnant - glm4 - 32b - GGUF --include "allura - org_remnant - glm4 - 32b - Q4_K_M.gguf" --local - dir ./

# Download split files
huggingface - cli download bartowski/allura - org_remnant - glm4 - 32b - GGUF --include "allura - org_remnant - glm4 - 32b - Q8_0/*" --local - dir ./

📚 Documentation

Model Information

Downloadable Files

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 to improve performance on ARM and AVX machines. Now, there is "online repacking" for weights. Details can be found 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, 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 increase.

Which File to Choose

A great write - up with charts showing various performances is provided by Artefact2 here. The first thing to figure out is how big your available memory is and what level of quality you need.

🔧 Technical Details

Quantization Process

The quantizations are done using llama.cpp release b5270. All quants are made using the imatrix option with a dataset from here.

Performance Benchmark

📄 License

This project is licensed under the Apache - 2.0 license.