$ -weight: 500;">curl -fsSL https://ollama.com/-weight: 500;">install.sh | sh -weight: 500;">systemctl -weight: 500;">start ollama ollama --version -weight: 500;">curl -fsSL https://ollama.com/-weight: 500;">install.sh | sh -weight: 500;">systemctl -weight: 500;">start ollama ollama --version -weight: 500;">curl -fsSL https://ollama.com/-weight: 500;">install.sh | sh -weight: 500;">systemctl -weight: 500;">start ollama ollama --version mkdir -p ~/Documents/LLM cd ~/Documents/LLM # Copy your .gguf file here mkdir -p ~/Documents/LLM cd ~/Documents/LLM # Copy your .gguf file here mkdir -p ~/Documents/LLM cd ~/Documents/LLM # Copy your .gguf file here vim Modelfile vim Modelfile vim Modelfile FROM ./Phi-4-mini-instruct-Q4_K_M.gguf SYSTEM """ You are a helpful AI assistant. """ TEMPLATE """<|user|> {{ .Prompt }}<|end|> <|assistant|> """ PARAMETER -weight: 500;">stop "<|user|>" PARAMETER -weight: 500;">stop "<|assistant|>" PARAMETER -weight: 500;">stop "<|end|>" PARAMETER temperature 0.7 PARAMETER num_ctx 8192 FROM ./Phi-4-mini-instruct-Q4_K_M.gguf SYSTEM """ You are a helpful AI assistant. """ TEMPLATE """<|user|> {{ .Prompt }}<|end|> <|assistant|> """ PARAMETER -weight: 500;">stop "<|user|>" PARAMETER -weight: 500;">stop "<|assistant|>" PARAMETER -weight: 500;">stop "<|end|>" PARAMETER temperature 0.7 PARAMETER num_ctx 8192 FROM ./Phi-4-mini-instruct-Q4_K_M.gguf SYSTEM """ You are a helpful AI assistant. """ TEMPLATE """<|user|> {{ .Prompt }}<|end|> <|assistant|> """ PARAMETER -weight: 500;">stop "<|user|>" PARAMETER -weight: 500;">stop "<|assistant|>" PARAMETER -weight: 500;">stop "<|end|>" PARAMETER temperature 0.7 PARAMETER num_ctx 8192 ollama create mymodel -f Modelfile ollama run mymodel ollama create mymodel -f Modelfile ollama run mymodel ollama create mymodel -f Modelfile ollama run mymodel # NVIDIA watch -n 1 nvidia-smi # AMD watch -n 1 rocm-smi # NVIDIA watch -n 1 nvidia-smi # AMD watch -n 1 rocm-smi # NVIDIA watch -n 1 nvidia-smi # AMD watch -n 1 rocm-smi journalctl -u ollama -f # Look for: "using CUDA" or "offloading layers to GPU" journalctl -u ollama -f # Look for: "using CUDA" or "offloading layers to GPU" journalctl -u ollama -f # Look for: "using CUDA" or "offloading layers to GPU" # Generate (single turn) -weight: 500;">curl http://localhost:11434/api/generate -d '{ "model": "mymodel", "prompt": "Explain Docker in simple terms", "stream": false }' # Chat (multi-turn) -weight: 500;">curl http://localhost:11434/api/chat -d '{ "model": "mymodel", "messages": [ { "role": "user", "content": "Hello!" } ] }' # List models via API -weight: 500;">curl http://localhost:11434/api/tags # Check running models -weight: 500;">curl http://localhost:11434/api/ps # Generate (single turn) -weight: 500;">curl http://localhost:11434/api/generate -d '{ "model": "mymodel", "prompt": "Explain Docker in simple terms", "stream": false }' # Chat (multi-turn) -weight: 500;">curl http://localhost:11434/api/chat -d '{ "model": "mymodel", "messages": [ { "role": "user", "content": "Hello!" } ] }' # List models via API -weight: 500;">curl http://localhost:11434/api/tags # Check running models -weight: 500;">curl http://localhost:11434/api/ps # Generate (single turn) -weight: 500;">curl http://localhost:11434/api/generate -d '{ "model": "mymodel", "prompt": "Explain Docker in simple terms", "stream": false }' # Chat (multi-turn) -weight: 500;">curl http://localhost:11434/api/chat -d '{ "model": "mymodel", "messages": [ { "role": "user", "content": "Hello!" } ] }' # List models via API -weight: 500;">curl http://localhost:11434/api/tags # Check running models -weight: 500;">curl http://localhost:11434/api/ps # Start Ollama -weight: 500;">service -weight: 500;">systemctl -weight: 500;">start ollama # Stop Ollama -weight: 500;">service -weight: 500;">systemctl -weight: 500;">stop ollama # Restart Ollama -weight: 500;">service -weight: 500;">systemctl -weight: 500;">restart ollama # Start Ollama -weight: 500;">service -weight: 500;">systemctl -weight: 500;">start ollama # Stop Ollama -weight: 500;">service -weight: 500;">systemctl -weight: 500;">stop ollama # Restart Ollama -weight: 500;">service -weight: 500;">systemctl -weight: 500;">restart ollama # Start Ollama -weight: 500;">service -weight: 500;">systemctl -weight: 500;">start ollama # Stop Ollama -weight: 500;">service -weight: 500;">systemctl -weight: 500;">stop ollama # Restart Ollama -weight: 500;">service -weight: 500;">systemctl -weight: 500;">restart ollama # Check -weight: 500;">service -weight: 500;">status -weight: 500;">systemctl -weight: 500;">status ollama # View live logs journalctl -u ollama -f # View last 50 log lines journalctl -u ollama -n 50 # Check -weight: 500;">service -weight: 500;">status -weight: 500;">systemctl -weight: 500;">status ollama # View live logs journalctl -u ollama -f # View last 50 log lines journalctl -u ollama -n 50 # Check -weight: 500;">service -weight: 500;">status -weight: 500;">systemctl -weight: 500;">status ollama # View live logs journalctl -u ollama -f # View last 50 log lines journalctl -u ollama -n 50 # Enable Ollama to -weight: 500;">start on boot -weight: 500;">systemctl -weight: 500;">enable ollama # Disable autostart -weight: 500;">systemctl -weight: 500;">disable ollama # Check if enabled -weight: 500;">systemctl is-enabled ollama # Enable Ollama to -weight: 500;">start on boot -weight: 500;">systemctl -weight: 500;">enable ollama # Disable autostart -weight: 500;">systemctl -weight: 500;">disable ollama # Check if enabled -weight: 500;">systemctl is-enabled ollama # Enable Ollama to -weight: 500;">start on boot -weight: 500;">systemctl -weight: 500;">enable ollama # Disable autostart -weight: 500;">systemctl -weight: 500;">disable ollama # Check if enabled -weight: 500;">systemctl is-enabled ollama -weight: 600;">sudo -weight: 500;">dnf -weight: 500;">install golang -y go version -weight: 600;">sudo -weight: 500;">dnf -weight: 500;">install golang -y go version -weight: 600;">sudo -weight: 500;">dnf -weight: 500;">install golang -y go version go -weight: 500;">install github.com/gaurav-gosain/gollama@latest # Add Go binaries to PATH echo 'export PATH=$PATH:~/go/bin' >> ~/.bashrc source ~/.bashrc go -weight: 500;">install github.com/gaurav-gosain/gollama@latest # Add Go binaries to PATH echo 'export PATH=$PATH:~/go/bin' >> ~/.bashrc source ~/.bashrc go -weight: 500;">install github.com/gaurav-gosain/gollama@latest # Add Go binaries to PATH echo 'export PATH=$PATH:~/go/bin' >> ~/.bashrc source ~/.bashrc - i — enter insert mode (-weight: 500;">start typing) - Esc — exit insert mode - :wq — save and quit - :q! — quit without saving