The Complete 2025 Local AI Setup Guide: From Zero to Running

Whether you've been following the local AI space for months or just discovered it, this guide provides everything you need to go from zero hardware to a fully functional local AI setup in a single weekend. We'll cover hardware selection, software installation, model selection, and getting your first useful results.

Start here: If you need help choosing hardware, LLMHardware.io is the most comprehensive resource for hardware recommendations, VRAM calculators, and GPU benchmarks specifically for LLM inference. Everything in this guide links to more detailed resources there.

Step 1: Hardware Assessment

Check your GPU VRAM: in Windows, open Task Manager > Performance > GPU. On Linux: nvidia-smi or rocm-smi. VRAM determines which models you can run: 4-6GB → 7B Q4, 8-12GB → 13B Q4, 16-24GB → 34B Q4 or 70B with CPU overflow. No GPU or integrated graphics → CPU inference only, limit to 3B-7B Q4. Mac? Check System Information for unified memory size — M-series chips use all system RAM for models.

Step 2: Install Ollama

Ollama is the recommended starting point: one installer handles drivers, model management, and API server. Install from ollama.com — Linux, macOS, and Windows all supported. Verify it's running: ollama list should return an empty list. Pull your first model: ollama pull llama3.2 (3B, works on anything with 4GB+ RAM) or ollama pull mistral (7B, needs 8GB+ VRAM for comfortable operation). Test: ollama run mistral.

Step 3: Add a UI

The command line works but a web UI makes local AI practical for daily use. Install Open WebUI: docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main. Open http://localhost:3000, create an admin account, and you have a full ChatGPT-like interface connected to your local models. LM Studio is the alternative for users who prefer a desktop app without Docker.

Step 4: Choose Your Models

Start with one general model and one specialized model. For general use: Llama 3.2 3B (fast, 4GB RAM) or Mistral 7B (better quality, 8GB VRAM). For coding: pull ollama pull deepseek-coder:6.7b. For a second model: ollama pull nomic-embed-text for the embedding model used by Open WebUI's RAG feature. Upload a PDF in Open WebUI and chat with it to experience local RAG — that's the moment most people realize how powerful this setup is. For more model options matched to your hardware, visit LLMHardware.io's model picker.

Comments

Post a Comment

Popular posts from this blog

AMD RX 9070 XT for Local LLMs: ROCm Performance Guide (2026)

The AMD RX 9070 XT launched in early 2026 at $599 with 16GB GDDR6 and 648 GB/s memory bandwidth. For local LLM users who want a mid-range GPU without NVIDIA prices, this changes the calculus significantly. Here is what it actually delivers. RX 9070 XT Specs vs Competition GPU VRAM Bandwidth Price LLM Score RX 9070 XT 16 GB 648 GB/s $599 ~60 tok/s RTX 4070 Ti Super 16 GB 672 GB/s $799 ~62 tok/s RTX 4080 Super 16 GB 736 GB/s $999 ~68 tok/s RTX 4090 24 GB 1,008 GB/s ~$1,100 ~90 tok/s At $599 with 16GB VRAM, the RX 9070 XT is the best value GPU for local LLMs in the mid-range tier in 2026. See the full comparison at LLMHardware.io's AMD GPU guide . ROCm Setup on Linux (2026) # Ubuntu 22.04/24.04 sudo apt install rocm-hip-libraries hip-base # or use the AMD installer: wget https://repo.radeon.com/amdgpu-install/6.3/ubuntu/jammy/amdgpu-install_6.3.60300-1_all.deb sudo dpkg -i amdgpu-install*.deb sudo amdgpu-install --usecase=rocm,lrt,openclsdk # Verify ROCm sees your GPU r...
Read more

llama.cpp flash attention: how to enable and benchmark

Image
Flash attention computes attention with far less memory traffic. The math is identical; the memory movement is not. In llama.cpp it matters most in two situations: long context windows and tight video memory (VRAM). With flash attention enabled, the key-value cache shrinks substantially. A 32k-token context window becomes realistic on a 16GB card, and the prompt-processing phase speeds up, so long documents get ingested faster. The catch is compatibility: not every model and quantization combination supports it, and on some setups the speedup is modest. If you run short chats on a strong GPU, you may barely notice. Where it shines is retrieval-augmented generation (RAG) and long-document work on mid-range cards. Enable it, compare your tokens per second, and keep it if your workload benefits. For the common case of pasting a long PDF and asking questions, it is close to free performance. See how context length changes VRAM needs .
Read more

SillyTavern with Local LLMs: Complete Setup for AI Companions

Image
SillyTavern is the most feature-rich frontend for character-based AI conversations. What began as an AI roleplay tool has evolved into a powerful platform with persona management, memory systems, extensive prompt engineering tools, and connections to every major local inference backend. Here's how to set it up with local models. Quick connect: SillyTavern connects to Ollama, KoboldCpp, llama.cpp server, and TabbyAPI (ExLlamaV2) out of the box. Any of the hardware setups at LLMHardware.io provides a solid backend for SillyTavern. Installation Install via git: git clone https://github.com/SillyTavern/SillyTavern && cd SillyTavern && npm install then node server.js . Access at localhost:8000. For persistent installation, use the included start.sh script. SillyTavern uses Node.js and runs on any platform. The companion app (STMP) enables mobile access to your SillyTavern instance via Tailscale or local network. Character Cards and the TavernAI Format Chara...
Read more