Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


Llama-3-MahouDevil-8B - GGUF
- Model creator: https://huggingface.co/lemon07r/
- Original model: https://huggingface.co/lemon07r/Llama-3-MahouDevil-8B/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Llama-3-MahouDevil-8B.Q2_K.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q2_K.gguf) | Q2_K | 2.96GB |
| [Llama-3-MahouDevil-8B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [Llama-3-MahouDevil-8B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [Llama-3-MahouDevil-8B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [Llama-3-MahouDevil-8B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [Llama-3-MahouDevil-8B.Q3_K.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q3_K.gguf) | Q3_K | 3.74GB |
| [Llama-3-MahouDevil-8B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [Llama-3-MahouDevil-8B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [Llama-3-MahouDevil-8B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [Llama-3-MahouDevil-8B.Q4_0.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q4_0.gguf) | Q4_0 | 4.34GB |
| [Llama-3-MahouDevil-8B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [Llama-3-MahouDevil-8B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [Llama-3-MahouDevil-8B.Q4_K.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q4_K.gguf) | Q4_K | 4.58GB |
| [Llama-3-MahouDevil-8B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [Llama-3-MahouDevil-8B.Q4_1.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q4_1.gguf) | Q4_1 | 4.78GB |
| [Llama-3-MahouDevil-8B.Q5_0.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q5_0.gguf) | Q5_0 | 5.21GB |
| [Llama-3-MahouDevil-8B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [Llama-3-MahouDevil-8B.Q5_K.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q5_K.gguf) | Q5_K | 5.34GB |
| [Llama-3-MahouDevil-8B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [Llama-3-MahouDevil-8B.Q5_1.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q5_1.gguf) | Q5_1 | 5.65GB |
| [Llama-3-MahouDevil-8B.Q6_K.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q6_K.gguf) | Q6_K | 6.14GB |
| [Llama-3-MahouDevil-8B.Q8_0.gguf](https://huggingface.co/RichardErkhov/lemon07r_-_Llama-3-MahouDevil-8B-gguf/blob/main/Llama-3-MahouDevil-8B.Q8_0.gguf) | Q8_0 | 7.95GB |




Original model description:
---
base_model:
- mlabonne/NeuralDaredevil-8B-abliterated
- flammenai/Mahou-1.2-llama3-8B
- flammenai/Mahou-1.3-llama3-8B
library_name: transformers
tags:
- mergekit
- merge
license: llama3
---
# Llama-3-MahouDevil-8B

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [mlabonne/NeuralDaredevil-8B-abliterated](https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated) as a base.

### Models Merged

The following models were included in the merge:
* [flammenai/Mahou-1.2-llama3-8B](https://huggingface.co/flammenai/Mahou-1.2-llama3-8B)
* [flammenai/Mahou-1.3-llama3-8B](https://huggingface.co/flammenai/Mahou-1.3-llama3-8B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: mlabonne/NeuralDaredevil-8B-abliterated
dtype: bfloat16
merge_method: model_stock
slices:
- sources:
  - layer_range: [0, 32]
    model: flammenai/Mahou-1.2-llama3-8B
  - layer_range: [0, 32]
    model: flammenai/Mahou-1.3-llama3-8B
  - layer_range: [0, 32]
    model: mlabonne/NeuralDaredevil-8B-abliterated
```