Tech Rants

Tech Rants

By Edward OjamboTechnology
Download on the App Store

All Tech Rants episodes

  • The VRAM Lie Nobody Talks About

    Your consumer GPU has twelve gigabytes of VRAM. Your AI model needs twenty four.


    The used enterprise market has the answer. Forty eight gigabytes for under one thousand two hundred dollars changes everything.


    I ran the benchmarks live on Fedora with real terminal output. The RTX A6000 swallows large language models that crash brand new consumer cards.


    Read the full breakdown and watch the screencast. Then build your stack with the resources below.


    Blog: https://ojambo.com/used-enterprise-gpus-vs-new-consumer-gpus-the-vram-reality-check-you-need

    Video: https://youtube.com/live/QkBK9zfyhPs

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #GPU #AI #SelfHosting

    1 hr 25 min
  • The Free Ebook Editor That Beats Paid Software

    Your ebook workflow is broken right now. Calibre editor fixes every formatting problem instantly.


    Professional publishers trust this open source tool. You get complete HTML and CSS control today.


    Blog: https://ojambo.com/calibre-ebook-editor-exposed-the-secret-weapon-professional-publishers-use

    Video: https://youtube.com/live/YZX3k35kbX0

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #EbookPublishing #Calibre #OpenSource

    32 min
  • MiniT2I Local AI: Run Text to Image on AMD GPU for FREE

    Your AMD GPU can generate images right now. Cloud APIs are costing you money every month.


    MiniT2I runs locally with stable-diffusion.cpp. The 258 million parameter model delivers professional results. ROCm and Vulkan backends accelerate everything on your Mi60.


    Blog: https://ojambo.com/run-minit2i-locally-on-amd-gpu-with-stable-diffusion-cpp-and-rocm

    Video: https://youtube.com/live/R2bXNiyMWuA

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #LocalAI #MiniT2I #AMDGPU

    1 hr 8 min
  • The Pandoc Secret That Fixes PDF Formatting Forever

    Your document conversion workflow is completely broken right now. The pandoc xelatex flag changes everything instantly.


    Every markdown file transforms into a polished PDF. Complex tables render perfectly without any manual tweaking required.


    Visit the blog for the complete technical breakdown. Watch the video for the live screencast demonstration.


    Blog: https://ojambo.com/convert-markdown-to-pdf-using-pandoc-without-breaking-a-sweat

    Video: https://youtube.com/live/WX5AirHs3D8

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #Pandoc #Markdown #PDFConversion

    1 hr 8 min
  • Five Dollar Pi Runs DOOM Self Hosted

    The Pi Zero W costs under five dollars. This board runs Chocolate Doom with perfect compatibility.


    The headless rendering configuration eliminates all desktop overhead. Your frame rates stay steady on minimal hardware.


    The build guide covers every compilation flag required. Network tethering enables reliable remote access for gaming.


    Blog: https://ojambo.com/five-dollar-pi-zero-w-runs-doom-self-hosted

    Video: https://youtube.com/live/QWEMIMy0Mcc

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #RaspberryPi #SelfHosting #RetroGaming

    58 min
  • SuperTux 0.7.0 Changed Open Source Gaming Forever

    The open source platformer revolution has arrived. SuperTux 0.7.0 delivers mechanics that commercial studios cannot replicate. Local multiplayer finally exists after twenty years. The level editor rivals professional creation tools. SimpleSquirrel scripting empowers modders to create custom content. This release proves community driven development produces superior results.


    Blog: https://ojambo.com/supertux-0-7-0-is-the-open-source-platformer-you-have-been-sleeping-on

    Video: https://youtube.com/live/UJ-QJtgKlH4

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #OpenSourceGaming #LinuxGaming #SuperTux

    1 hr 3 min
  • The Local AI Voice Revolution Is Here

    Cloud text to speech APIs are dying. Local voice cloning runs on your hardware now.


    qwentts.cpp delivers studio quality speech synthesis offline. Eleven languages and voice design are included.


    Blog: https://ojambo.com/this-local-text-to-speech-tool-changes-everything-for-voice-cloning

    Video: https://youtube.com/live/kvd0DKHG53c

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #LocalAI #VoiceCloning #TextToSpeech

    1 hr 24 min
  • The AI Rust Code Vulnerability Crisis No One Is Talking About

    Your AI generated Rust code compiles cleanly. The tests pass without errors. But critical vulnerabilities hide inside unsafe blocks that the compiler completely ignores.


    Forty five percent of AI generated code introduces security flaws according to Veracode testing. Rust developers need a systematic audit process before deployment.


    Blog: https://ojambo.com/your-ai-generated-rust-code-is-a-time-bomb

    Video: https://youtube.com/live/jHVgOEVa_5k

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #Rust #AISecurity #CodeAudit

    45 min
  • Enterprise GPUs Destroy Consumer Cards For Local AI Workloads

    Consumer GPUs cannot load large language models into VRAM. Enterprise accelerator cards solve this problem completely.


    The AMD Instinct MI60 delivers thirty two gigabytes of HBM2 memory. Used Nvidia cards offer FP8 Tensor Core acceleration for professional workloads.


    Blog: https://ojambo.com/enterprise-gpus-like-amd-mi60-vs-consumer-gpus-plus-used-nvidia-enterprise-cards-for-llms-stable-diffusion-and-gaming

    Video: https://youtube.com/live/fPIDgwgz-QM

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #EnterpriseGPU #LocalLLM #AIHardware

    1 hr 44 min
  • The Secret Backend War Vulkan vs ROCM for Local AI

    Local AI image generation has a hidden bottleneck. Your GPU backend choice determines everything.


    I tested the Lens model on AMD hardware live. The results changed how I build every AI pipeline.


    Read the full technical breakdown and watch the live stream. Master the theory with books and build your workspace with blueprints.


    Blog: https://ojambo.com/the-absolute-secret-to-instant-generative-ai-with-stable-diffusion-cpp-lens-model-using-vulkan-and-rocm-on-amd-gpus

    Video: https://youtube.com/live/sWpdxrG9YR4

    Books: https://www.amazon.com/stores/Edward-Ojambo/author/B0D94QM76N

    Woodworking Blueprints: https://ojamboshop.com

    Tutorials: https://ojambo.com/contact

    Consultations: https://ojamboservices.com/contact


    #LocalAI #AMDGPU #StableDiffusion

    2 hr 21 min