Views
No views yet
Loki-Omega-70B-6QMerged.gguf (57GB) - Full merged model, ready to use1pip install "llama-cpp-python[server]"
2python -m llama_cpp.server \
3 --model /path/to/Loki-Omega-70B-6QMerged.gguf \
4 --host 0.0.0.0 --port 8000 \
5 --n_ctx 32000
6
7## Quantization: Q6_K (maintains quality and nuance)
8Note: This is the merged version. For split files, see the original repository.
9