license: apache-2.0
library_name: llama.cpp
pipeline_tag: text-generation
tags:
- gguf
- quantized
- cybersecurity
- uncensored
- q3_K_M
base_model: llmfan46/gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic
gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-Q3_K_M
Credits & License
This is a quantized and *converted from safetensors to .gguf version of an existing *.safetensor model. (And size of it converted from 24GB to 5.53GB)
So it can be used on CPU with 8GB of RAM (better 16GB. Also can be run on Google Colab).
Lineage:
- Original Model: llmfan46/gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic (License: Apache 2.0)
My Contribution:
- Convert from safetensors to *.gguf
- Quantized that GGUF file into Q3_K_M formats to reduce RAM usage for inference.
- Alarm: Quantized version can hallucinate.
- Recommended context window: 1024 tokens (or higher if hardware permits).
License:
This derivative work is distributed under the Apache 2.0 license, inherited from the original model.
Please refer to the original model card for full terms and disclaimer.
Donation address (if you want to see more quantized uncensored models - or in future create of more uncensored model):
1Kk32KvJVjcyTMZ44eos4eZtme1quTqFAg (BTC)