license: llama3
language:
- en
tags: - roleplay
- llama3
- sillytavern
- idol
- TensorBlock
- GGUF
base_model: aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored
aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored - GGUF
This repo contains GGUF format model files for aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Our projects
| Forge | |
|---|---|
|
|
| An OpenAI-compatible multi-provider routing layer. | |
| 🚀 Try it now! 🚀 | |
| Awesome MCP Servers | TensorBlock Studio |
 |
 |
| A comprehensive collection of Model Context Protocol (MCP) servers. | A lightweight, open, and extensible multi-LLM interaction studio. |
| 👀 See what we built 👀 | 👀 See what we built 👀 |
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q2_K.gguf | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q3_K_S.gguf | Q3_K_S | 3.664 GB | very small, high quality loss |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q3_K_M.gguf | Q3_K_M | 4.019 GB | very small, high quality loss |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q3_K_L.gguf | Q3_K_L | 4.322 GB | small, substantial quality loss |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q4_0.gguf | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q4_K_S.gguf | Q4_K_S | 4.693 GB | small, greater quality loss |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q4_K_M.gguf | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q5_0.gguf | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q5_K_S.gguf | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q5_K_M.gguf | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q6_K.gguf | Q6_K | 6.596 GB | very large, extremely low quality loss |
| DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q8_0.gguf | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-GGUF --include "DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-Q2_K.gguf" --local-dir MY_LOCAL_DIR
If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:
huggingface-cli download tensorblock/DarkIdol-Llama-3.1-8B-Instruct-1.1-Uncensored-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'