
How do I load a local GGUF model into Odysseus?
Hi, I installed Odysseus on Linux (CachyOS). and I want to use a local GGUF model that I downloaded manually from Hugging Face.
Model:llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning.i1-Q6_K.gguf
I specifically want to use only the i1-Q6_K quantized version (6.6 GB) — not another quantization or automatic download.
I already have the .gguf file downloaded. from here https://huggingface.co/mradermacher/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-i1-GGUF
What is the correct way to make Odysseus detect and use it?