Self hosted ai

A single-file C engine called Colibrì streams GLM-5.2's 744B mixture-of-experts weights off an NVMe drive to run the full model on 25 GB of RAM at 0.05-2 tokens/second. Here's how it works, what Hacker News made of it, and how to check on a queued run from your phone with Pinggy.

OpenMontage is the world's first open-source agentic video production system. Learn how it works, how to set it up for free, and how to share Remotion previews online with Pinggy.

whichllm auto-detects your GPU, CPU, and RAM, then ranks local models by real benchmarks rather than parameter count. Here's how to use it, run your pick with Ollama, and share it remotely via Pinggy.

A practical hardware guide for self-hosting LLMs in 2026. Compare consumer GPUs, Apple Silicon, enterprise cards, and pre-built AI workstations. Find the right setup for 7B to 405B models at every budget.

The best open-weight coding LLMs you can self-host as of October 2026, from MiMo-V2.6-Pro and GLM-5.3 down to Qwen3.8-27B on one GPU, with current benchmark scores, licenses and the hardware each one needs.

Discover the best open-source alternatives to ChatGPT in 2026. Compare Open WebUI, Jan, GPT4All, LibreChat, LobeChat, AnythingLLM, and more self-hosted AI chat platforms you can run locally with full privacy.

Complete guide to self-hosting large language models locally using Ollama and Open WebUI with Docker. Learn to run AI models privately with full control over your data.

Learn how to run Jan, a ChatGPT alternative, locally and share it online using Pinggy. Complete guide to setting up your private AI assistant.

The best local LLM tools in 2026 (LM Studio, Unsloth, Ollama, LocalAI and more) and the open-weight models that fit in 128GB of memory, with measured 4-bit sizes for Qwen3.8, Gemma 4 and gpt-oss.

Learn how to run powerful DeepSeek AI models locally on your computer using Ollama for privacy-focused, cost-effective AI development with data control.