Thedrummer Fallen Gemma3 4B V1 GGUF

🚀 Llamacpp imatrix Quantizations of Fallen-Gemma3-4B-v1 by TheDrummer

This project provides Llama.cpp imatrix quantizations of the Fallen-Gemma3-4B-v1 model. It offers various quantization types to meet different performance and quality requirements, and can be run in LM Studio or directly with Llama.cpp.

🚀 Quick Start

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

✨ Features

• Multiple Quantization Types: Offers a wide range of quantization types, such as BF16, Q8_0, Q6_K_L, etc., to balance between quality and file size.
• Optimized for Different Hardware: Some quantizations are optimized for ARM and AVX machines, and support online repacking for better performance.
• Easy to Download: You can download specific files using the Hugging Face CLI.

📦 Installation

Installing Hugging Face CLI

First, make sure you have the Hugging Face CLI installed:

pip install -U "huggingface_hub[cli]"

Downloading Specific Files

You can target the specific file you want:

huggingface-cli download bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF --include "TheDrummer_Fallen-Gemma3-4B-v1-Q4_K_M.gguf" --local-dir ./

Downloading Split Files

If the model is bigger than 50GB and split into multiple files, run:

huggingface-cli download bartowski/TheDrummer_Fallen-Gemma3-4B-v1-GGUF --include "TheDrummer_Fallen-Gemma3-4B-v1-Q8_0/*" --local-dir ./

💻 Usage Examples

Prompt Format

<bos><start_of_turn>user
{system_prompt}

{prompt}<end_of_turn>
<start_of_turn>model
<end_of_turn>
<start_of_turn>model

📚 Documentation

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 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 Method: Using llama.cpp release b4925 for quantization.
• Original Model: The original model is TheDrummer/Fallen-Gemma3-4B-v1.
• Calibration Dataset: All quants are made using the imatrix option with the dataset from here.

📄 License

This project is under the other 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.

If you want to support my work, visit my ko-fi page here: https://ko-fi.com/bartowski