Mlabonne Qwen3 0.6B Abliterated GGUF

🚀 Llamacpp imatrix Quantizations of Qwen3-0.6B-abliterated by mlabonne

This project provides quantized versions of the Qwen3-0.6B-abliterated model using llama.cpp, offering various quantization types for different performance and quality requirements.

🚀 Quick Start

• Using llama.cpp release b5228 for quantization.
• Original model: https://huggingface.co/mlabonne/Qwen3-0.6B-abliterated
• All quants made using imatrix option with dataset from here
• Run them in LM Studio
• Run them directly with llama.cpp, or any other llama.cpp based project

✨ Features

• Multiple Quantization Types: Offers a wide range of quantization types (e.g., bf16, Q8_0, Q6_K_L, etc.) to meet different performance and quality needs.
• Embed/Output Weights Optimization: Some quantizations use Q8_0 for embeddings and output weights to improve quality.
• Online Repacking: Supports online repacking for ARM and AVX machines to enhance performance.

📦 Installation

Downloading using huggingface-cli

pip install -U "huggingface_hub[cli]"

huggingface-cli download bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF --include "mlabonne_Qwen3-0.6B-abliterated-Q4_K_M.gguf" --local-dir ./

huggingface-cli download bartowski/mlabonne_Qwen3-0.6B-abliterated-GGUF --include "mlabonne_Qwen3-0.6B-abliterated-Q8_0/*" --local-dir ./

💻 Usage Examples

Prompt format

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

📚 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?