These are my personal testing quants for flammenai/Mahou-1.2-llama3-8B.
I recommend checking the author's card for more information.
Some SillyTavern presets [ChatML].

GGUF

Model size

8.03B params

Architecture

llama

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API

Inference API (serverless) has been turned off for this model.