Tech Couch

A Comfy Corner for Software, Security, Cloud, and AI

Written by engineers, not ai

ai

Sorting email inboxes with local LLMs

Categorizing by message contents without sacrificing privacy

Setting up Local LLM voice conversations

Talking with your graphics card in real-time

Understanding the different sizes of ai models

Making sense of differing model sizes and variations

Enabling gpu support in docker

Accelerating video and machine learning workloads inside containers

Running local text to speech using chatterbox

Multi-language text to speech with optional voice cloning without external services

An overview of C2PA

Adding more metadata to images

A guide to ai model file formats

Making sense of the different file extensions

Running LLMs locally with ollama

Painless AI text models on localhost

Removing image backgrounds with python and ai

Automating a common image editing task with ai

Optimizing SQL queries with ChatGPT

Take advantage of ChatGPT's processing capabilities to make sense of complex query costs and optimization opportunities