tensorblock/soob3123_amoral-gemma3-12B-v2-GGUF

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

soob3123/amoral-gemma3-12B-v2 - GGUF

This repo contains GGUF format model files for soob3123/amoral-gemma3-12B-v2.

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

Our projects

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

<bos><start_of_turn>user
{system_prompt}

{prompt}<end_of_turn>
<start_of_turn>model

Model file specification

Filename	Quant type	File Size	Description
amoral-gemma3-12B-v2-Q2_K.gguf	Q2_K	4.768 GB	smallest, significant quality loss - not recommended for most purposes
amoral-gemma3-12B-v2-Q3_K_S.gguf	Q3_K_S	5.458 GB	very small, high quality loss
amoral-gemma3-12B-v2-Q3_K_M.gguf	Q3_K_M	6.009 GB	very small, high quality loss
amoral-gemma3-12B-v2-Q3_K_L.gguf	Q3_K_L	6.480 GB	small, substantial quality loss
amoral-gemma3-12B-v2-Q4_0.gguf	Q4_0	6.887 GB	legacy; small, very high quality loss - prefer using Q3_K_M
amoral-gemma3-12B-v2-Q4_K_S.gguf	Q4_K_S	6.935 GB	small, greater quality loss
amoral-gemma3-12B-v2-Q4_K_M.gguf	Q4_K_M	7.301 GB	medium, balanced quality - recommended
amoral-gemma3-12B-v2-Q5_0.gguf	Q5_0	8.232 GB	legacy; medium, balanced quality - prefer using Q4_K_M
amoral-gemma3-12B-v2-Q5_K_S.gguf	Q5_K_S	8.232 GB	large, low quality loss - recommended
amoral-gemma3-12B-v2-Q5_K_M.gguf	Q5_K_M	8.445 GB	large, very low quality loss - recommended
amoral-gemma3-12B-v2-Q6_K.gguf	Q6_K	9.661 GB	very large, extremely low quality loss
amoral-gemma3-12B-v2-Q8_0.gguf	Q8_0	12.510 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/soob3123_amoral-gemma3-12B-v2-GGUF --include "amoral-gemma3-12B-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/soob3123_amoral-gemma3-12B-v2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'