Edit model card
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

TeamUNIVA/Komodo_6B_v3.0.0 - GGUF

This repo contains GGUF format model files for TeamUNIVA/Komodo_6B_v3.0.0.

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
Komodo_6B_v3.0.0-Q2_K.gguf Q2_K 2.240 GB smallest, significant quality loss - not recommended for most purposes
Komodo_6B_v3.0.0-Q3_K_S.gguf Q3_K_S 2.592 GB very small, high quality loss
Komodo_6B_v3.0.0-Q3_K_M.gguf Q3_K_M 2.857 GB very small, high quality loss
Komodo_6B_v3.0.0-Q3_K_L.gguf Q3_K_L 3.084 GB small, substantial quality loss
Komodo_6B_v3.0.0-Q4_0.gguf Q4_0 3.317 GB legacy; small, very high quality loss - prefer using Q3_K_M
Komodo_6B_v3.0.0-Q4_K_S.gguf Q4_K_S 3.339 GB small, greater quality loss
Komodo_6B_v3.0.0-Q4_K_M.gguf Q4_K_M 3.498 GB medium, balanced quality - recommended
Komodo_6B_v3.0.0-Q5_0.gguf Q5_0 3.999 GB legacy; medium, balanced quality - prefer using Q4_K_M
Komodo_6B_v3.0.0-Q5_K_S.gguf Q5_K_S 3.999 GB large, low quality loss - recommended
Komodo_6B_v3.0.0-Q5_K_M.gguf Q5_K_M 4.092 GB large, very low quality loss - recommended
Komodo_6B_v3.0.0-Q6_K.gguf Q6_K 4.724 GB very large, extremely low quality loss
Komodo_6B_v3.0.0-Q8_0.gguf Q8_0 6.117 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/Komodo_6B_v3.0.0-GGUF --include "Komodo_6B_v3.0.0-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/Komodo_6B_v3.0.0-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
207
GGUF
Model size
6.18B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/Komodo_6B_v3.0.0-GGUF

Quantized
(1)
this model