GV

GeezerVison

The World Wide Web, restored to 800 pixels of glory.

Home|About|Gaming cabinet|Archives|How it works|Starter sites

On this site

  • Add
  • Follow
  • News
  • PC Hardware
  • CPU
  • GPU
  • Storage
  • Software
  • AI tools
  • Productivity
  • Self-Hosting
  • Home Lab
  • Other Software
  • OS and Devices

This view

  • Original page
  • New address

GeezerVison is showing www.xda-developers.com — Artificial Intelligence | XDA

Artificial Intelligence

Follow
Followed

latest

OpenWhispr on Windows 11
I tried 3 open-source alternatives to Otter for my meeting notes, and one runs entirely on my PC
Self-Hosting

Because open-source doesn't always mean private

Posts
By  Abhinav Raj
LFM3-Omni running on an M2 Mac Air
My 8GB laptop now runs an AI that can see and talk, and it never goes online

Small LLMs are doing less for more, and I'm here for it

Posts
By  Abhinav Raj
qwythos in lm studio with filesystem mcp on desktop pc
I gave my local AI model access to my personal documents, and it finally became more useful than a chatbot

The model I trust most with my files isn't the one I pay for

Posts
By  Nolen Jonker
qwen 3.5 9b filesystem in lm studio on desktop pc
I stopped trying to make one local LLM do everything, and that's when it got useful

My default model was spread too thin

Posts
By  Nolen Jonker
Llama.cpp running on a Lian-Li 8.8-inch display besides a GeForce RTX GPU.
I spent $300 in one month trying to get past Claude's rate limits, so I let my GPU do the coding first instead
Claude

My credit card shouldn't be the only workaround to fix a disrupted workflow

Posts 2
By  Abhinav Raj
using copilot ai and web viewer in obsidian on desktop pc
I turned Obsidian into an AI browser, and it does what Gemini in Chrome does without my research leaving my vault
AI tools

The browser I use for private work isn't actually a real browser

Posts
By  Nolen Jonker
bonsai 27b in lm studio on desktop pc
I stopped chasing bigger local models, and a 27B model on my 8GB GPU does more of what I need

I don't download every new model anymore

Posts 8
By  Nolen Jonker
OpenCode harness running Qwen3.6 35B A3B
I expected Claude Code to crush its open-source rival on my 16GB GPU, but that’s not what happened

Agentic AI isn't blocked by a paywall anymore

Posts
By  Abhinav Raj
Codex, Antigravity, and Chrome Extensions on screen
I made Claude Code, Codex, and Antigravity build the same Chrome extension, and only one was a keeper

One prompt was all it took to reveal which AI coding tool understood the assignment best.

Posts 20
By  Yash Patel
Running Locally by LM Studio on an iPhone, running Gemma 4 26B
I replaced Gemini and ChatGPT on my phone with my gaming PC’s 26B model, and the app that does it is free

Farewell, bloated AI apps!

Posts 13
By  Abhinav Raj
Llama.cpp serving Qwen3.6 on a Windows 11 PC.
4 jobs my local AI handles for free that I would never trust with a cloud model

Not all my information is meant to reach OpenAI's servers

Posts
By  Abhinav Raj
Using Writing Tools with Qwen3.6-35B-A3B
I replaced Grammarly Pro with a local model on my GPU, and my drafts never leave my PC

My local LLM replaces yet another subscription for effectively $0

Posts 1
By  Abhinav Raj
Serving Qwen3.6 35B A3B via llama.cpp through home network
My gaming GPU sat idle most of the day, so I turned it into a local AI server the whole house can use

One Llama.cpp command can turn your PC into an AI server, and it really is that easy

Posts 3
By  Abhinav Raj
OpenCode running on Mac
I learned Godot by letting LLMs guide me, not code for me

Vibe coding is faster, but where's the fun in that?

Posts
By  Simon Batt
upscayl app with ai models on desktop pc
I ditched ComfyUI for a local image tool that does exactly what I need

Sometimes the boring tiny job deserves its own app

Posts
By  Nolen Jonker
Claude Code on a Legion 5 Pro laptop.
I let Claude Code debloat my 4-year-old Windows laptop, and it found 30 GB of junk I never needed
Windows 11: Everything you need to know

Sonnet 5.5 is a better debloater than most paid apps

Posts
By  Abhinav Raj
Running local AI inference on a GPU, peak power draw from CPU and GPU displayed on an 8.8-inch display
I measured my local LLM’s power bill and it costs less than a single $20 ChatGPT, Claude or Gemini subscription

The math isn't close, and it never really was

Posts 8
By  Abhinav Raj
qwen in noema on iphone 16
My phone runs a local 2B model that searches the web, and Perplexity feels pointless now

A small model that has web is a powerful model

Posts 1
By  Nolen Jonker
AI tools on Lenovo Legion
5 unusual AI tricks I use to get better results than a single prompt ever could

I've stopped chasing better AI models and started using smarter tricks to get better results.

Posts
By  Yash Patel
llama.cpp running on Windows PowerShell and MacOS CLI
I changed two settings in my local AI setup, and stopped needing more VRAM

Is your GPU to blame, or your runtime's defaults?

Posts 3
By  Abhinav Raj
See More   See More

Subscribe to the AI newsletter for clear, actionable insights

Subscribing gives you focused coverage of artificial intelligence: accessible explainers, trend analysis, ethical and policy perspectives, and concrete use cases—everything you need to understand AI developments and their implications.

By subscribing, you agree to receive newsletter and marketing emails, and accept our Terms of Use and Privacy Policy. You can unsubscribe anytime.

Unlock Personalized Content & Exclusive Features

  • Engage in discussions in Threads
  • Follow and Like top authors, topics, and trends
  • Browse with fewer ads across the site
  • Personalize your profile to showcase your activity
  • Get a content feed tailored to your interests

Thank you for subscribing to our newsletter,

[email protected] Complete Your Registration
  • Today's best deals

Shokz OpenRun Pro
The Shokz OpenRun Pro open-ear sport headphones drop to $100 at Best Buy
asus-usb-ax55-nano header
Upgrade your PC's wireless speeds for just $30 with this ASUS Wi-Fi 6 adapter
Razer DeathAdder V3 Pro
The Razer DeathAdder V3 Pro usually flies under the radar, but the 47% discount is going to bring some attention
See More
You are visitor 01402503 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.