LLM: ollama install ubuntu 24.04 python open-webio
Sumber: https://www.jeremymorgan.com/blog/generative-ai/local-llm-ubuntu/
Pastikan:
- OS bisa linux server, seperti ubuntu server.
- Memory RAM pastikan cukup untuk menyimpan model-nya. Model llama3 butuh memory paling tidak 8GB.
- Kalau mau lebih enak/lebih cepat sebaiknya pakai GPU, seperti nvidia telsa yang agak baru.
Install aplikasi pendukung
sudo apt update sudo apt install curl net-tools
Download
sudo curl -fsSL https://ollama.com/install.sh | sh
Sebagai user biasa run & download model
ollama pull llama3.3:1b ollama pull llama3 ollama pull deepseek-r1:7b ollama pull qwen2.5-coder:7b ollama pull bge-m3:latest ollama pull gemma3:4b
ollama pull adijayainc/bhsa-deepseek-r1-1.5b ollama pull adijayainc/bhsa-llama3.2
optional,
ollama pull llama3.2:1b
ollama pull rizkiagungid/deeprasx ollama pull fyandono/chatbot-id ollama pull rexyb10/codeai ollama pull fahlevi20/DeepSeek-R1-TechSchole-Indonesia
ollama pull all-MiniLM
Kalau punya GPU dengan RAM besar
ollama pull llama3.3
Cek ollama
systemctl status ollama
Install docker open-webui
sudo apt install ffmpeg
sudo su curl -LsSf https://astral.sh/uv/install.sh | sh source $HOME/.local/bin/env
sudo su DATA_DIR=~/.open-webui uvx --python 3.11 open-webui@latest serve
Step 2: Managing Your Ollama Instance To manage your Ollama instance in Open WebUI, follow these steps:
- Go to Admin Settings in Open WebUI.
- Navigate to Connections > Ollama > Manage (click the wrench icon).
From here, you can download models, configure settings, and manage your connection to Ollama.
Contoh
curl http://localhost:11434/api/generate -d '{ "model" : "llama3", "prompt" : "tell me a joke", "stream" : false }'