Local LLMs
10 pieces on Local LLMs, including 8 step-by-step guides.
Guides
The Complete Developer Guide to Running LLMs Locally: From Ollama to Production
Everything you need to run LLMs on your own hardware in 2026: VRAM sizing, model formats, an 8-tool comparison table, a full local RAG pipeline, and Docker production deployment with GPU passthrough and Nginx auth.
How to Run DeepSeek R1 Locally with Ollama: Full Setup Guide
Install DeepSeek R1 locally using Ollama in under 5 minutes. Covers model variant selection from 1.5B to 671B, visible chain-of-thought reasoning, REST API usage, Python integration, and building a simple RAG application.
Run DeepSeek V4 Flash Locally with llama.cpp on a Single GPU
Step-by-step guide to running the full DeepSeek V4 Flash GGUF locally on a single RTX Pro 6000 GPU using a modified llama.cpp build, llama-server, and the Hugging Face hf_transfer downloader.
How to Run Qwen3 Locally with Ollama: Setup, API, and a Gradio App
Set up Qwen3 locally in minutes using Ollama. Covers every model variant, thinking mode control with /think and /no_think tags, CLI, REST API, Python SDK, and a practical Gradio reasoning app.
Self-Hosting DeepSeek V4 with vLLM: Hardware Requirements and Deployment Guide
Deploy DeepSeek V4-Flash or V4-Pro on your own infrastructure. Covers hardware requirements (VRAM budgets, GPU configs), vLLM setup, expert parallelism, quantization trade-offs, AWS instance selection, and a break-even cost analysis.
Run Claude Code Locally with Ollama: A Complete Setup Guide
Learn how to set up a fully local AI coding agent by connecting Claude Code to Ollama and running open-source models like GLM 4.7 Flash — no cloud, no API costs, full privacy.
Building AI Agents with Local Small Language Models (SLMs)
Learn how to build fully functional, private AI agents on your own hardware using Ollama and LangChain with lightweight models under 10B parameters.
How to Run Local LLMs Securely Using Ollama
A step-by-step tutorial on installing Ollama, pulling models like Llama 3, and running private queries without data leaks.
News & Analysis
Qwen 3.8 27B Is Capable but Defaults to Extreme Overthinking
Alibaba's Apache 2.0-licensed 27B vision model fits in 17 GB and handles agents, vision, and code — but its xhigh reasoning default is a trap.
Structured Output with Local LLMs: When Valid JSON Is Not Enough
Gemma 4's 4B model returns schema-valid JSON that still includes the wrong device. Here's the decomposition pattern that fixes it.