metadata
license: other
tags:
- TensorBlock
- GGUF
base_model: TheDrummer/Cydonia-24B-v2
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
TheDrummer/Cydonia-24B-v2 - GGUF
This repo contains GGUF format model files for TheDrummer/Cydonia-24B-v2.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4658.
Prompt template
Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| Cydonia-24B-v2-Q2_K.gguf | Q2_K | 8.890 GB | smallest, significant quality loss - not recommended for most purposes |
| Cydonia-24B-v2-Q3_K_S.gguf | Q3_K_S | 10.400 GB | very small, high quality loss |
| Cydonia-24B-v2-Q3_K_M.gguf | Q3_K_M | 11.474 GB | very small, high quality loss |
| Cydonia-24B-v2-Q3_K_L.gguf | Q3_K_L | 12.401 GB | small, substantial quality loss |
| Cydonia-24B-v2-Q4_0.gguf | Q4_0 | 13.442 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| Cydonia-24B-v2-Q4_K_S.gguf | Q4_K_S | 13.549 GB | small, greater quality loss |
| Cydonia-24B-v2-Q4_K_M.gguf | Q4_K_M | 14.334 GB | medium, balanced quality - recommended |
| Cydonia-24B-v2-Q5_0.gguf | Q5_0 | 16.304 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| Cydonia-24B-v2-Q5_K_S.gguf | Q5_K_S | 16.304 GB | large, low quality loss - recommended |
| Cydonia-24B-v2-Q5_K_M.gguf | Q5_K_M | 16.764 GB | large, very low quality loss - recommended |
| Cydonia-24B-v2-Q6_K.gguf | Q6_K | 19.346 GB | very large, extremely low quality loss |
| Cydonia-24B-v2-Q8_0.gguf | Q8_0 | 25.055 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/Cydonia-24B-v2-GGUF --include "Cydonia-24B-v2-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/Cydonia-24B-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'