RichardErkhov/Rupesh2_-_Llama-3.1-8B-Uncensored-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.1-8B-Uncensored - GGUF

• Model creator: https://huggingface.co/Rupesh2/
• Original model: https://huggingface.co/Rupesh2/Llama-3.1-8B-Uncensored/

Name	Quant method	Size
Llama-3.1-8B-Uncensored.Q2_K.gguf	Q2_K	2.96GB
Llama-3.1-8B-Uncensored.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama-3.1-8B-Uncensored.IQ3_S.gguf	IQ3_S	3.43GB
Llama-3.1-8B-Uncensored.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama-3.1-8B-Uncensored.IQ3_M.gguf	IQ3_M	3.52GB
Llama-3.1-8B-Uncensored.Q3_K.gguf	Q3_K	3.74GB
Llama-3.1-8B-Uncensored.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama-3.1-8B-Uncensored.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama-3.1-8B-Uncensored.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3.1-8B-Uncensored.Q4_0.gguf	Q4_0	4.34GB
Llama-3.1-8B-Uncensored.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3.1-8B-Uncensored.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama-3.1-8B-Uncensored.Q4_K.gguf	Q4_K	4.58GB
Llama-3.1-8B-Uncensored.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama-3.1-8B-Uncensored.Q4_1.gguf	Q4_1	4.78GB
Llama-3.1-8B-Uncensored.Q5_0.gguf	Q5_0	5.21GB
Llama-3.1-8B-Uncensored.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama-3.1-8B-Uncensored.Q5_K.gguf	Q5_K	5.34GB
Llama-3.1-8B-Uncensored.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama-3.1-8B-Uncensored.Q5_1.gguf	Q5_1	5.65GB
Llama-3.1-8B-Uncensored.Q6_K.gguf	Q6_K	6.14GB
Llama-3.1-8B-Uncensored.Q8_0.gguf	Q8_0	7.95GB

Original model description:

license: apache-2.0 tags: - merge - mergekit - lazymergekit - Orenguteng/Llama-3-8B-Lexi-Uncensored - aifeifei798/llama3-8B-DarkIdol-2.3-Uncensored-32K

Llama-3.1-8B-Uncensored

Llama-3.1-8B-Uncensored is a merge of the following models using mergekit:

• Orenguteng/Llama-3-8B-Lexi-Uncensored
• aifeifei798/llama3-8B-DarkIdol-2.3-Uncensored-32K

🧩 Configuration

```yaml models:

• model: meta-llama/Meta-Llama-3.1-8B-Instruct
• model: Orenguteng/Llama-3-8B-Lexi-Uncensored parameters: density: 0.53 weight: 0.6
• model: aifeifei798/llama3-8B-DarkIdol-2.3-Uncensored-32K parameters: density: 0.53 weight: 0.4 merge_method: dare_ties base_model: meta-llama/Meta-Llama-3.1-8B-Instruct parameters: int8_mask: true dtype: bfloat16 ```