This repository contains a single merged GGUF file for running ReadyArt/L3.3-The-Omega-Directive-70B-Unslop-v2.0 with llama.cpp (Q6_K quantization).

File

Loki-Omega-70B-6QMerged.gguf (57GB) - Full merged model, ready to use

Quick Start (llama.cpp server, OpenAI-compatible)

bash

pip install "llama-cpp-python[server]"
python -m llama_cpp.server \
  --model /path/to/Loki-Omega-70B-6QMerged.gguf \
  --host 0.0.0.0 --port 8000 \
  --n_ctx 32000

## Quantization: Q6_K (maintains quality and nuance)
Note: This is the merged version. For split files, see the original repository.

Babsie/Loki-Omega-70B-6QMerged-GGUF

Loki-Omega-70B-6QMerged-GGUF

File

Quick Start (llama.cpp server, OpenAI-compatible)

Babsie/
Loki-Omega-70B-6QMerged-GGUF