LLM Tutorials

Learn how to run Fable 5-Enhanced Gemma 4 locally with prebuilt llama.cpp binaries on an RTX 5070 Ti, test MTP speculative decoding, connect Pi for private AI coding-agent workflows, and troubleshoot common setup issues.

Learn how to run Kimi K2.7 Code locally in five minutes with the prebuilt llama.cpp binary on four RTX PRO 6000 GPUs, then use its web UI and Pi coding agent through an OpenAI-compatible API.

Learn how to run MiniMax M3 locally on two RTX PRO 6000 GPUs with llama.cpp, test its OpenAI-compatible API and web UI, and connect it to Pi Coding Agent for private, high-speed local coding workflows.

Learn how Claude Code routines run your coding agent in the cloud on a schedule or a GitHub event, so PR reviews and audits finish with your laptop closed.

GGUF packages model weights, tokenizer data, and metadata into a single portable file. Learn how to choose the right quantization level and get started with Ollama.

Learn how to accelerate local Gemma 4 31B inference on a single RTX 4090 using DFlash speculative decoding and Flash Attention against a baseline setup.

Build a Streamlit app that runs Claude Opus 4.8 with adaptive thinking, auto-scores each response with Haiku 4.5, and charts the cost-quality tradeoff.

Set up a multi-GPU Docker environment with tensor parallelism and EAGLE speculative decoding to serve Mistral Medium 3.5 128B through an OpenAI-compatible API.

Run Qwen3.6 27B on an RTX 3090 and learn how Multi-Token Prediction (MTP) with llama.cpp can boost local LLM inference by almost 2x without upgrading your GPU.

Learn how OpenAI's gpt-realtime-2, gpt-realtime-translate, and gpt-realtime-whisper differ, then test each one with working Python WebSocket code.

Learn how to run the full DeepSeek V4 Flash model on a single GPU using a modified llama.cpp build and a compatible GGUF file in this hands-on tutorial.

Learn how DeepSeek V4's three reasoning modes work, and build a Streamlit comparison app that shows when each mode actually wins on quality, speed, and cost.