---
license: apache-2.0
base_model:
- n0ctyx/wifuGPT-1.7B
tags:
- gguf
- uncensored
- waifu
- qwen3
- roleplay
- chat
- nsfw
---

![image](https://cdn-uploads.huggingface.co/production/uploads/69c5a300c7262fff2700db4a/uPCWLvbTgcLMib_-Xf6-D.png)

# wifuGPT-1.7B GGUF

GGUF quantizations of [n0ctyx/wifuGPT-1.7B](https://huggingface.co/n0ctyx/wifuGPT-1.7B). For use with Ollama, llama.cpp, LM Studio, KoboldCpp, etc.

| File | Quant | Size |
|------|-------|------|
| wifuGPT-1.7B-Q4_K_M.gguf | Q4_K_M | 1.1 GB |
| wifuGPT-1.7B-BF16.gguf | BF16 | 3.3 GB |

## Download

For the best experience, download using `huggingface-cli` and then create the Ollama model from the local file:
```bash
pip install -U huggingface_hub
hf download n0ctyx/wifuGPT-1.7B-GGUF wifuGPT-1.7B-Q4_K_M.gguf --local-dir .
```

## Ollama

Create a `Modelfile`:                                                                                                                                                 
```Modelfile                                              
  FROM ./wifuGPT-1.7B-Q4_K_M.gguf
  PARAMETER temperature 0.7                                                                                                                                             
  PARAMETER top_p 0.8
  TEMPLATE """{{- range .Messages }}                                                                                                                                    
  <|im_start|>{{ .Role }}                                   
  {{ .Content }}<|im_end|>                                                                                                                                              
  {{ end }}                                                 
  <|im_start|>assistant                                                                                                                                                 
  <think>                                                   
                                                                                                                                                                        
  </think>
  """                                               
```
```bash
  ollama create wifugpt -f Modelfile                                                                                                                                    
  ollama run
```

## llama.cpp

```bash
./llama-cli -m wifuGPT-1.7B-Q4_K_M.gguf -p "Hey!" -n 512
```

| Variant | Repo | Size |
|---------|------|------|
| bf16 safetensors | [n0ctyx/wifuGPT-1.7B](https://huggingface.co/n0ctyx/wifuGPT-1.7B) | 3.4 GB |
| 4-bit safetensors | [n0ctyx/wifuGPT-1.7B-4bit](https://huggingface.co/n0ctyx/wifuGPT-1.7B-4bit) | 1.35 GB |
| **GGUF (this)** | [n0ctyx/wifuGPT-1.7B-GGUF](https://huggingface.co/n0ctyx/wifuGPT-1.7B-GGUF) | 1.1 / 3.3 GB |

## Disclaimer

Contains explicit adult content. Use responsibly.

---

## pssst~ wanna help out? 💕

hii so um... making these models takes like SO many GPU hours and my wallet is literally crying rn 😭 between abliterating, generating datasets, fine-tuning, and quantizing -- it all adds up super fast (,,>_<,,)

if this model made you smile (or blush~) maybe buy me a coffee?? it keeps the GPUs warm and the models coming ✨

[![Buy Me A Coffee](https://img.shields.io/badge/Buy%20Me%20A%20Coffee-ffdd00?style=for-the-badge&logo=buy-me-a-coffee&logoColor=black)](https://buymeacoffee.com/n0ctyx)

every coffee = more cute uncensored models for everyone~ tysm 💗