---
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
library_name: transformers
tags:
- mergekit
- merge
- TensorBlock
- GGUF
---
## Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B - GGUF
This repo contains GGUF format model files for [Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B](https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B).
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
## Prompt template
```
<|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 |
| -------- | ---------- | --------- | ----------- |
| [L3-Umbral-Mind-RP-v3.0-8B-Q2_K.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
| [L3-Umbral-Mind-RP-v3.0-8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
| [L3-Umbral-Mind-RP-v3.0-8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
| [L3-Umbral-Mind-RP-v3.0-8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
| [L3-Umbral-Mind-RP-v3.0-8B-Q4_0.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [L3-Umbral-Mind-RP-v3.0-8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
| [L3-Umbral-Mind-RP-v3.0-8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
| [L3-Umbral-Mind-RP-v3.0-8B-Q5_0.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [L3-Umbral-Mind-RP-v3.0-8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
| [L3-Umbral-Mind-RP-v3.0-8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
| [L3-Umbral-Mind-RP-v3.0-8B-Q6_K.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
| [L3-Umbral-Mind-RP-v3.0-8B-Q8_0.gguf](https://huggingface.co/tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF/tree/main/L3-Umbral-Mind-RP-v3.0-8B-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
## Downloading instruction
### Command line
Firstly, install Huggingface Client
```shell
pip install -U "huggingface_hub[cli]"
```
Then, downoad the individual model file the a local directory
```shell
huggingface-cli download tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF --include "L3-Umbral-Mind-RP-v3.0-8B-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:
```shell
huggingface-cli download tensorblock/L3-Umbral-Mind-RP-v3.0-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```