tensorblock/allura-org_Q3-30b-A3b-Pentiment-GGUF

allura-org/Q3-30b-A3b-Pentiment - GGUF

Join our Discord to learn more about what we're building ↗

This repo contains GGUF format model files for allura-org/Q3-30b-A3b-Pentiment.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.

Our projects

Forge
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
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 👀

Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename	Quant type	File Size	Description
Q3-30b-A3b-Pentiment-Q2_K.gguf	Q2_K	11.259 GB	smallest, significant quality loss - not recommended for most purposes
Q3-30b-A3b-Pentiment-Q3_K_S.gguf	Q3_K_S	13.292 GB	very small, high quality loss
Q3-30b-A3b-Pentiment-Q3_K_M.gguf	Q3_K_M	14.712 GB	very small, high quality loss
Q3-30b-A3b-Pentiment-Q3_K_L.gguf	Q3_K_L	15.901 GB	small, substantial quality loss
Q3-30b-A3b-Pentiment-Q4_0.gguf	Q4_0	17.304 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Q3-30b-A3b-Pentiment-Q4_K_S.gguf	Q4_K_S	17.456 GB	small, greater quality loss
Q3-30b-A3b-Pentiment-Q4_K_M.gguf	Q4_K_M	18.557 GB	medium, balanced quality - recommended
Q3-30b-A3b-Pentiment-Q5_0.gguf	Q5_0	21.081 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Q3-30b-A3b-Pentiment-Q5_K_S.gguf	Q5_K_S	21.081 GB	large, low quality loss - recommended
Q3-30b-A3b-Pentiment-Q5_K_M.gguf	Q5_K_M	21.726 GB	large, very low quality loss - recommended
Q3-30b-A3b-Pentiment-Q6_K.gguf	Q6_K	25.093 GB	very large, extremely low quality loss
Q3-30b-A3b-Pentiment-Q8_0.gguf	Q8_0	32.484 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/allura-org_Q3-30b-A3b-Pentiment-GGUF --include "Q3-30b-A3b-Pentiment-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/allura-org_Q3-30b-A3b-Pentiment-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'