LLM on Raspberry Pi and Jetson: What a Small Board Can Really Run in 2026
Can you run an LLM on Raspberry Pi 5 or a Jetson Orin Nano Super? Bandwidth limits, model sizes, prices and when a small PC or used GPU is the better buy.
-
-
vLLM Tutorial: Serving Local LLMs With vLLM and SGLang When Ollama Is Not Enough
A vLLM tutorial for local LLM serving: when vLLM or SGLang beats Ollama, how PagedAttention and batching work, install and serve commands, and VRAM planning.
-
Home AI Server: How to Build a Private LLM Box for Your NAS and Network
Build a home AI server for local LLMs: hardware tiers, Docker setup with Ollama and Open WebUI, NAS storage, remote access and the security steps that matter.
-
LLM Rig Power and Cooling: PSU Sizing, Power Limits and Airflow for a Local AI PC
LLM rig power and cooling guide: how to size the PSU, use nvidia-smi power limits, plan airflow and noise, and avoid the mistakes that crash a GPU server.
-
Local LLM API Server: Turn Ollama or llama.cpp Into an OpenAI-Compatible Endpoint
Local LLM API server guide: expose Ollama or llama-server as an OpenAI-compatible endpoint, test it with curl and Python, and keep it safe on your network.
-
Local LoRA Fine-Tuning VRAM: How Much GPU Memory You Need for QLoRA and LoRA
Local LoRA fine-tuning VRAM explained: Unsloth minimums for QLoRA vs LoRA from 3B to 70B, what raises memory use, and the levers that fix training OOM.
-
MLX vs llama.cpp on Mac: Which Runtime Should You Use for Local LLMs on Apple Silicon?
MLX vs llama.cpp on Mac: how mlx-lm and GGUF tools differ on Apple silicon, install steps, model formats, memory limits and which one to choose.
-
家用 AI 服务器：怎样搭一台给全家用的私有大模型主机（含 NAS 与远程访问）
家用 AI 服务器怎么搭：硬件分档、Docker 部署 Ollama 与 Open WebUI、NAS 如何配合、外网访问方式，以及必须做的安全设置。
-
大模型主机供电与散热：电源选型、功耗限制与风道规划
大模型主机供电与散热指南：如何给 AI 电脑选电源、用 nvidia-smi 限制功耗、规划风道和噪音，避开让显卡主机宕机的常见错误。
-
本地大模型 API 服务搭建：把 Ollama 或 llama.cpp 变成兼容 OpenAI 的接口
本地大模型 API 服务搭建指南：把 Ollama 或 llama-server 变成兼容 OpenAI 的接口，用 curl 和 Python 测试，并在局域网里安全地开放访问。
