2026-07-31 · 11 min
TAG
How-To
18 posts tagged “how-to”
2026-07-31 · 9 min
How to run DeepSeek locally
2026-07-30 · 11 min
Batch-process 10,000 documents locally for the cost of electricity
2026-07-29 · 11 min
Offline voice assistant with Whisper + a local LLM
2026-07-28 · 12 min
Run a private RAG knowledge base on a single GPU
2026-07-27 · 11 min
Build a private coding agent that never phones home
2026-07-26 · 10 min
Self-host your own 'ChatGPT' for $300
2026-07-24 · 16 min
How to run AI models locally in 2026: the complete setup
2026-07-19 · 11 min
Best local LLM for coding in 2026: measured
2026-07-19 · 13 min
ComfyUI optimization in 2026: Dynamic VRAM, quantization, and attention backends explained
2026-07-19 · 13 min
CUDA vs ROCm vs Vulkan vs OpenVINO: measured
2026-07-19 · 12 min
Home AI server: a working four-node fleet
2026-07-19 · 12 min
Local video generation in 2026: Wan, Hunyuan, and CogVideoX on your own GPU
2026-07-19 · 11 min
Ollama vs llama.cpp on the same hardware: measured
2026-07-19 · 11 min
Running Flux and Stable Diffusion locally: the honest cost and hardware guide
2026-07-19 · 12 min
Speculative decoding on consumer GPUs: MTP measured 2.07×
2026-07-19 · 10 min
What a quantization tier costs in watts: measured
2026-07-18 · 8 min