---
base_model: Khetterman/AbominationScience-12B-v4
pipeline_tag: text-generation
library_name: transformers
quantized_by: Khetterman
tags:
- mergekit
- merge
- 12b
- chat
- creative
- roleplay
- conversational
- creative-writing
- not-for-all-audiences
language:
- en
- ru

---
# AbominationScience-12B-v4 GGUF Quantizations 🗲

>When the choice is not random.

![AbominationScienceLogo256.png](https://cdn-uploads.huggingface.co/production/uploads/673125091920e70ac26c8a2e/8-0Z-4VoJxQxjKX_kgCG0.png)

This model was converted to GGUF format using [llama.cpp](https://github.com/ggerganov/llama.cpp).

For more information of the model, see the original model card: [Khetterman/AbominationScience-12B-v4](https://huggingface.co/Khetterman/AbominationScience-12B-v4).

## Available Quantizations (◕‿◕) 

|  Type  | Quantized GGUF Model | Size |
|--------|----------------------|------|
| Q4_0   | [Khetterman/AbominationScience-12B-v4-Q4_0.gguf](https://huggingface.co/Khetterman/AbominationScience-12B-v4-GGUF/blob/main/AbominationScience-12B-v4-Q4_0.gguf) | 6.58 GiB |
| Q6_K   | [Khetterman/AbominationScience-12B-v4-Q6_K.gguf](https://huggingface.co/Khetterman/AbominationScience-12B-v4-GGUF/blob/main/AbominationScience-12B-v4-Q6_K.gguf) | 9.36 GiB |
| Q8_0   | [Khetterman/AbominationScience-12B-v4-Q8_0.gguf](https://huggingface.co/Khetterman/AbominationScience-12B-v4-GGUF/blob/main/AbominationScience-12B-v4-Q8_0.gguf) | 12.1 GiB |

>My thanks to the authors of the original models, your work is incredible. Have a good time 🖤