AI & Local LLMs SeriesNew part

Local LLMs & Self-Hosted AI

Run LLMs locally on Linux: Ollama, Open WebUI, DeepSeek R1, Ollama CLI reference, and open-source model comparisons.

Start with Part 1 → 9 parts · 2 hr 33 min total · read in order
Local LLMs & Self-Hosted AI
  1. 1 Install Ollama on Rocky Linux 10 / Ubuntu 24.04 Part 1 of 9

    Install Ollama on Rocky Linux 10 / Ubuntu 24.04

    Running large language models on your own hardware means no API costs, no data leaving your network, and no rate limits. Ollama makes this straightforward with…

    15 min read·Mar 2026
  2. 2 Install Open WebUI with Ollama on Linux Part 2 of 9

    Install Open WebUI with Ollama on Linux

    Running your own ChatGPT-like interface on hardware you control is no longer a weekend project for tinkerers. Open WebUI (formerly Ollama WebUI) has crossed 124,000 GitHub…

    13 min read·Mar 2026
  3. 3 Ollama Commands Cheat Sheet: CLI and API Reference Part 3 of 9

    Ollama Commands Cheat Sheet: CLI and API Reference

    Every time I need to check a model’s parameter count or hit the embedding endpoint, I end up scrolling through docs. This cheat sheet is the…

    19 min read·Mar 2026
  4. 4 Run DeepSeek R1 Locally with Ollama on Linux Part 4 of 9

    Run DeepSeek R1 Locally with Ollama on Linux

    DeepSeek R1 does something most open-source models skip: it shows its reasoning. When you ask it a question, it thinks through the problem step by step…

    11 min read·Mar 2026
  5. 5 Open Source LLM Comparison Table (2026) Part 5 of 9

    Open Source LLM Comparison Table (2026)

    The open-source LLM landscape has shifted dramatically. Models like Qwen 3.5, DeepSeek V3.2, GLM-5, and Llama 4 now match or beat proprietary alternatives on key benchmarks,…

    15 min read·Mar 2026
  6. 6 Ollama Models Cheat Sheet 2026 (gpt-oss, Qwen3-Coder, DeepSeek) Part 6 of 9

    Ollama Models Cheat Sheet 2026 (gpt-oss, Qwen3-Coder, DeepSeek)

    Ollama makes running open-weight LLMs locally as easy as ollama run, but the hard part is picking which model to run. Which hardware runs it is…

    32 min read·May 2026
  7. 7 Install and Use Unsloth Studio for No-Code LLM Fine-Tuning Part 7 of 9

    Install and Use Unsloth Studio for No-Code LLM Fine-Tuning

    Unsloth Studio puts the whole fine-tune in a browser. You pick a base model, drop in a dataset, choose QLoRA, click a button, and watch the…

    9 min read·Jun 2026
  8. 8 Self-Hosted RAG Pipeline with Ollama and pgvector (No API Keys) Part 8 of 9

    Self-Hosted RAG Pipeline with Ollama and pgvector (No API Keys)

    This guide builds a Retrieval Augmented Generation pipeline that runs entirely on your hardware. No OpenAI key, no Anthropic key, no telemetry. PostgreSQL with pgvector stores…

    21 min read·May 2026
  9. 9 Fine-Tune an LLM with Unsloth: QLoRA on a Single GPU Part 9 of 9

    Fine-Tune an LLM with Unsloth: QLoRA on a Single GPU

    A QLoRA fine-tune of Llama 3.1 8B finished in about 34 seconds on a single RTX 4090, and the peak GPU memory it touched was 6.6…

    18 min read·Jun 2026

More AI & Local LLMs series

Local AI Hardware 10

Press ESC to close