Kyllene
Collection
Model series for RPG/ERP • 4 items • Updated • 4
How to use TeeZee/Kyllene-34B-v1.1-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M
docker model run hf.co/TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M
How to use TeeZee/Kyllene-34B-v1.1-GGUF with Ollama:
ollama run hf.co/TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M
How to use TeeZee/Kyllene-34B-v1.1-GGUF with Docker Model Runner:
docker model run hf.co/TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M
How to use TeeZee/Kyllene-34B-v1.1-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull TeeZee/Kyllene-34B-v1.1-GGUF:Q4_K_M
lemonade run user.Kyllene-34B-v1.1-GGUF-Q4_K_M
lemonade list
GGUF quants of TeeZee/Kyllene-34B-v1.1, remeber to set your max context length to proper length for your hardware, 4096 is fine. Default context length is 200k so it will eat RAM or VRAM like crazy if left unchecked.
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit