metadata
license: other
base_model: OEvortex/MediKAI
tags:
- TensorBlock
- GGUF
Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
OEvortex/MediKAI - GGUF
This repo contains GGUF format model files for OEvortex/MediKAI.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
Prompt template
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| MediKAI-Q2_K.gguf | Q2_K | 5.125 GB | smallest, significant quality loss - not recommended for most purposes |
| MediKAI-Q3_K_S.gguf | Q3_K_S | 5.925 GB | very small, high quality loss |
| MediKAI-Q3_K_M.gguf | Q3_K_M | 6.552 GB | very small, high quality loss |
| MediKAI-Q3_K_L.gguf | Q3_K_L | 7.085 GB | small, substantial quality loss |
| MediKAI-Q4_0.gguf | Q4_0 | 7.569 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| MediKAI-Q4_K_S.gguf | Q4_K_S | 7.627 GB | small, greater quality loss |
| MediKAI-Q4_K_M.gguf | Q4_K_M | 8.076 GB | medium, balanced quality - recommended |
| MediKAI-Q5_0.gguf | Q5_0 | 9.115 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| MediKAI-Q5_K_S.gguf | Q5_K_S | 9.115 GB | large, low quality loss - recommended |
| MediKAI-Q5_K_M.gguf | Q5_K_M | 9.377 GB | large, very low quality loss - recommended |
| MediKAI-Q6_K.gguf | Q6_K | 10.759 GB | very large, extremely low quality loss |
| MediKAI-Q8_0.gguf | Q8_0 | 13.933 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/MediKAI-GGUF --include "MediKAI-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/MediKAI-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'