tensorblock/LLM360_K2-GGUF

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

LLM360/K2 - GGUF

This repo contains GGUF format model files for LLM360/K2.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5165.

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 👀

Unable to determine prompt format automatically. Please check the original model repository for the correct prompt format.

Filename	Quant type	File Size	Description
K2-Q2_K.gguf	Q2_K	24.113 GB	smallest, significant quality loss - not recommended for most purposes
K2-Q3_K_S.gguf	Q3_K_S	28.161 GB	very small, high quality loss
K2-Q3_K_M.gguf	Q3_K_M	31.632 GB	very small, high quality loss
K2-Q3_K_L.gguf	Q3_K_L	34.649 GB	small, substantial quality loss
K2-Q4_0.gguf	Q4_0	36.796 GB	legacy; small, very high quality loss - prefer using Q3_K_M
K2-Q4_K_S.gguf	Q4_K_S	37.055 GB	small, greater quality loss
K2-Q4_K_M.gguf	Q4_K_M	39.348 GB	medium, balanced quality - recommended
K2-Q5_0.gguf	Q5_0	44.924 GB	legacy; medium, balanced quality - prefer using Q4_K_M
K2-Q5_K_S.gguf	Q5_K_S	44.924 GB	large, low quality loss - recommended
K2-Q5_K_M.gguf	Q5_K_M	46.239 GB	large, very low quality loss - recommended
K2-Q6_K	Q6_K	53.560 GB	very large, extremely low quality loss
K2-Q8_0	Q8_0	69.371 GB	very large, extremely low quality loss - not recommended

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/LLM360_K2-GGUF --include "K2-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/LLM360_K2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'