Duplicated from ggml-org/gemma-4-31B-GGUF
How to use ipsarkar/gemma-4-31B-BF16-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 ipsarkar/gemma-4-31B-BF16-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf ipsarkar/gemma-4-31B-BF16-GGUF:BF16
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ipsarkar/gemma-4-31B-BF16-GGUF:BF16 # Run inference directly in the terminal: llama cli -hf ipsarkar/gemma-4-31B-BF16-GGUF:BF16
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf ipsarkar/gemma-4-31B-BF16-GGUF:BF16 # Run inference directly in the terminal: ./build/bin/llama cli -hf ipsarkar/gemma-4-31B-BF16-GGUF:BF16
docker model run hf.co/ipsarkar/gemma-4-31B-BF16-GGUF:BF16
How to use ipsarkar/gemma-4-31B-BF16-GGUF with vLLM:
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ipsarkar/gemma-4-31B-BF16-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ipsarkar/gemma-4-31B-BF16-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'
How to use ipsarkar/gemma-4-31B-BF16-GGUF with Ollama:
ollama run hf.co/ipsarkar/gemma-4-31B-BF16-GGUF:BF16
How to use ipsarkar/gemma-4-31B-BF16-GGUF with Docker Model Runner:
How to use ipsarkar/gemma-4-31B-BF16-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ipsarkar/gemma-4-31B-BF16-GGUF:BF16
lemonade run user.gemma-4-31B-BF16-GGUF-BF16
lemonade list
