Hot Config

Gemma4

Gemma4-12 v2 Inspection.. Can we get a powerhouse LLM inside a 8GB.. You decide.

We review a mucle-tuned powerhouse of a homeLLM. The rocking 8GB Gemma4-v2 tuned for coders and agentic tasks.

feed parser

Producthunt.com and a Feed Parser

This super simple RSS Feed Parser will enable you to examine RSS feeds very easily.

Nvidia Driver cuda nvcc Troubleshooting

We had so many issues troubleshooting and getting our Nvidia drivers to work with our particular kernel of Linux (ParrotOS latest) that we wrote this guide. Pretty much every LLM needs the full suite of drivers/nvcc etc, so this guide might help you - with your current Linux kernel.

MTP

World First! The Tom Pulls TurboQuant w/MTP (and it Works!)

A world first! TurboQuant + MTP support from the same LLama.cpp! What a game changer!

game

Asteroids. Written by AI in 1 Hour

Asteroids written by AI. Have fun!

MTP

Into the MTP Zone.. A Look at Multi-Token-Prediction - It Rocks!

We foray into MTP (Multiple Token Prediciton)

benchmarking

LocalLLM BenchMaxxing! How to Benchmark llama.cpp and power juice your localLLMs!

We go over benchmaxxing your localLLM in a custom Llama.cpp!

localLLM

LLMQP Drops! A New Queue Dispatcher. Let your LLM CODE ALL NIGHT.

LLM Queue Dispatcher. A Powerful Harness Drop will queue your localLLM all night and keep it working!

MCP Server

Agentic Server Primer: Llama.cpp MCP Lesson 10: mcp-coder (Cuda Version)

We build a MCP Coding Agent that will allow your LLM to specifically work on and debug it's own code with nvcc, or really any language!

MTP

MTP / TurboQuant Forked Llama.cpp

We hot compile one of the first combo MTP / TurboQuant forks in the world!

docker-compose.yml

docker-compose.yml -> docker run Converter

This page is a bookmarker. Need a docker-compose.yml converted to a docker run command on the fly? Here you go!

docker

Agentic Server Primer: Llama.cpp MCP Lesson 9: Docker Orchestrator

In this guide we go over letting your llm manage and create it's own docker images, stand up it's own containers after writing it's code. It uses a special docker-compose tool we built for it.

studentLLM

StudentLLM - Qwen2.5-coder-7b-instruct-q6-k / Qwen3.5 Agentic on a Ryzen 5-2600/ 3060ti. Production LLM or not? YES!

We Look a StudentLLM setup to get as much productivity out of limited hardware as we can.

One-shot

Qwen3.6 Drops!- A HouseLLM Production Level Coding Perspective? One-Shot GoAccess

We Test Qwen3.6 if it is up to your home production standards.

docker

PowerChest home Agent Agents MCP Tools to Put your HouseLLM into Turbo. MCP TOOLS 1-9++

Downloads Page for all your MCP tooling needs!

House LLM

Agentic Server Primer: Llama.cpp MCP Lesson 8: Process Manager Web Enabled Research Assistant w/ Code Drop.

Agentic Server Primer: Llama.cpp MCP Lesson 8: Process Manager Web Enabled Research Assistant

agentic server

Agentic Server Primer: Llama.cpp MCP Lesson 7: Process Manager (Part 1)

docker

Agentic Server Primer: Llama.cpp MCP Lesson 6: Adding mysql Database Docker Toolsets.

We give our LLM it's own Database to play with!

javascript

Agentic Server Primer: Llama.cpp MCP Lesson 5: Adding javascript via a Python api plugin.

We go through a full working example of creating your own MCP tools.

Qwen3-Coder

Qwen3-Coder-Next-UD-Q4-K_XL.gguf on a Ryzen 9/4080ti. Run a 48GB SOTA Tensor-Balanced on a $2K set of House Parts.

We field test a Qwen3-Coder-Next-UD-Q4_K_XL.gguf

llmfit

llmfit - Fast LLM Metric Fitter and Pulling Tool

We have a look at a fast fitting tool for comparing our hardware to the LLM market.

Qwen3.5

Qwen3.5-122B-A10B-Q4_K_M.gguf - Run it at 13 Tokens/s with 262,000 Contexts on a Ryzen 9 3900 and a 4080ti. w/128GB RAM.

agentic

Agentic Server Primer: Llama.cpp MCP Lesson 4: Weather Polling via api.weather.gov

House LLM

Agentic Server Primer: Llama.cpp MCP Lesson 3: Adding Python Tooling Capability To your HouseLLM.

Agentic Server Primer: Llama.cpp MCP Lesson 3: Python

docker

Agentic Server Primer: Llama.cpp MCP Lesson 2: Dockerization.