Best GPU for Local AI (2026)
Cornerstone WikiWayne guide: Best GPU for Local AI (2026). Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
Local AI
Open-weight models, local inference stacks, VRAM planning, and homelab setups for running AI on your own hardware.
Local AI topical hub
Best Used GPUs for Local AI on a Budget (2026)
Shopping the secondary market without overspending on VRAM you cannot use.
9 min read Jun 13, 2026
Your First ComfyUI Workflow for Local SDXL
Load checkpoints, wire KSampler, export PNGs locally.
8 min read Jun 13, 2026
ComfyUI Local Stable Diffusion Guide
Cornerstone WikiWayne guide: ComfyUI Local Stable Diffusion Guide. Open-weight, practitioner-tested local AI.
9 min read Jun 13, 2026
GPU Offload Layers Explained for Local LLMs
What `-ngl` / GPU layer sliders actually do.
8 min read Jun 13, 2026
Homelab Docker Stack: Ollama + Open WebUI
Compose services for local chat without cloud relay.
8 min read Jun 13, 2026
How Much VRAM for Llama 3 8B?
Quant-specific VRAM bands for Meta Llama 3 8B class models.
8 min read Jun 13, 2026
Install Ollama on Windows, Mac, and Linux (2026)
Step-by-step Ollama install paths for the three major desktop OS families.
8 min read Jun 13, 2026
KoboldCpp Creative Writing Setup
Import GGUF and tune narrative sampling locally.
8 min read Jun 13, 2026
KoboldCpp Local LLM Guide
Cornerstone WikiWayne guide: KoboldCpp Local LLM Guide. Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
llama.cpp CUDA Build Quickstart on Linux
Compile with GPU backends for NVIDIA cards.
8 min read Jun 13, 2026
llama.cpp Complete Guide
Cornerstone WikiWayne guide: llama.cpp Complete Guide. Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
llama.cpp vs Ollama: When to Switch
Leave the managed service when you need custom builds or flags.
7 min read Jun 13, 2026
LM Studio: Download Models Step by Step
Use the LM Studio catalog without guessing quant labels.
8 min read Jun 13, 2026
LM Studio vs Ollama vs llama.cpp: Which Local AI Tool?
Cornerstone WikiWayne guide: LM Studio vs Ollama vs llama.cpp: Which Local AI Tool?. Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
Local AI Model Tracker (2026)
Cornerstone WikiWayne guide: Local AI Model Tracker (2026). Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
Local LLM Checklist: Keep Data Off the Cloud
Network egress, logging, and backup habits for homelabs.
9 min read Jun 13, 2026
MLX on Apple Silicon for Local AI
Cornerstone WikiWayne guide: MLX on Apple Silicon for Local AI. Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
Install MLX on Apple Silicon for Local Llama
Python venv, mlx-lm, and a tiny model smoke test.
8 min read Jun 13, 2026
NVIDIA vs AMD GPU for Local LLMs (2026)
CUDA maturity vs ROCm tradeoffs for GGUF stacks.
7 min read Jun 13, 2026
Ollama OpenAI-Compatible API for Local Apps
Point agents and UIs at `http://localhost:11434/v1`.
7 min read Jun 13, 2026
Open WebUI for Local AI
Cornerstone WikiWayne guide: Open WebUI for Local AI. Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
Open WebUI + Ollama Connection Guide
Docker and bare-metal pairing for household chat.
7 min read Jun 13, 2026
Pull Your First Open-Weight Model in Five Minutes
From zero to a working chat with a small Ollama tag.
8 min read Jun 13, 2026
Q4 vs Q8 Quant Quality Tradeoffs
When to spend extra gigabytes on higher precision.
8 min read Jun 13, 2026
Quantization Explained for Local AI
Cornerstone WikiWayne guide: Quantization Explained for Local AI. Open-weight, practitioner-tested local AI.
9 min read Jun 13, 2026
Raspberry Pi 5 and Small LLM Limits
What runs at usable speed on 8 GB Pi hardware.
8 min read Jun 13, 2026
Raspberry Pi Local AI: Limits and Use Cases
Cornerstone WikiWayne guide: Raspberry Pi Local AI: Limits and Use Cases. Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
Run Open-Weight Models Locally (2026)
Cornerstone WikiWayne guide: Run Open-Weight Models Locally (2026). Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
VRAM Requirements for Local LLMs
Cornerstone WikiWayne guide: VRAM Requirements for Local LLMs. Open-weight, practitioner-tested local AI.
8 min read Jun 13, 2026
What Is GGUF? The Local LLM File Format Explained
GGUF packs tensors and metadata for llama.cpp-compatible runners.
8 min read Jun 13, 2026
Ollama vs LM Studio (2026): Which Local AI Runner Fits Your Workflow?
Ollama favors CLI and API automation; LM Studio favors GUI model browsing. Compare setup, VRAM use, and GGUF workflows on real hardware.
8 min read Jun 13, 2026
Self-Hosting for Beginners: Run Your Own Services in 2026
A complete guide to self-hosting your own services in 2026 — from hardware and Docker to Nextcloud, Vaultwarden, and OpenClaw on a Raspberry Pi or VPS.
13 min read Feb 25, 2026