LMSA Blog
Articles about AI, local models, and building intelligent applications with LMSA.
Your Local LLM Just Got a Real Voice
If you've used Voice Mode in LMSA, you know the drill. You tap the mic, say something, your phone transcribes it locally, your model thinks it through, and then Android's built-in text-to-speech reads the answer back to you. It works. It's private. It's also, if we're honest, a little robotic. That's changing today. LMSA now supports premium, privacy-first AI voice models that power both Voice Mode and text-to-speech playback in your chat history — and they run entirely on your Android device,
Read More →
How to Install LM Studio on Windows, Mac, and Linux (A Beginner's Guide)
If you've ever wanted to chat with an AI model without sending your data off to some company's server, LM Studio is one of the easiest ways to get there. It's a free desktop app that lets you download open-source language models and run them entirely on your own computer — no internet connection required once a model is downloaded, no subscription, and no one looking over your shoulder. The good news is that installing it is genuinely simple, even if you've never touched a terminal in your life
Read More →
LMSA Won't Connect to LM Studio? 10 Fixes That Actually Work
You've got LM Studio running, a model loaded, the server started, and LMSA still throws "Connection Failed" or just spins forever. It's one of the most common hiccups people hit when setting up local AI on Android, and the good news is that it almost always comes down to one of a small handful of causes. Work through these in order and you'll almost certainly find the culprit before you get to the bottom of the list. 1. Enable "Serve on Local Network" in LM Studio This is the fix that trips u
Read More →
Best Uncensored GGUF Models for 8GB VRAM in 2026
This guide goes through what's actually sitting at the top of the charts today, what fits an 8GB card cleanly, and what needs a workaround (or a bigger card) to run well.
Read More →
How Students Can Use Local AI for Studying Without Sending Data to the Cloud
Somewhere on your campus right now, a nursing student is pasting patient case notes into ChatGPT to build a study guide. A grad student is uploading a half-finished thesis chapter to get feedback before a meeting with their advisor. A pre-med student is dropping lecture slides full of exam content into a chatbot to generate practice questions. None of them are doing anything malicious. Most of them have never been told there's a problem with any of this. But there is a problem, and it's bigger
Read More →
How Much RAM/VRAM Do You Need to Run 7B, 13B, and 70B Models Locally?
If you've spent any time in local AI communities, you've probably seen this question asked a hundred different ways: "Can my GPU run this model?" "Will 16GB of RAM be enough?" "Why did my download just crash my whole computer?" The honest answer is that model size and memory requirements aren't as simple as matching gigabytes to parameter counts. Quantization, context length, and the difference between VRAM and system RAM all change the math significantly. This guide breaks down exactly what yo
Read More →
Why I Run Claude Code and Google AI Pro Side by Side
This one's just my opinion, based on how I actually work day to day. I'm not here to tell you what to buy. I'm here to tell you why I personally keep two AI coding subscriptions running instead of one, and why I think it's worth it even though you could absolutely get by with just one. I do most of my coding through two setups: Antigravity for Gemini, and Claude Code for Claude. Both are genuinely good. Both give me a solid set of tools to actually get work done instead of just chatting back an
Read More →
How to Actually Use LLM Leaderboards (Instead of Just Staring at Them)
If you've spent any time researching large language models, you've probably landed on a leaderboard at some point — a long table of model names, scores, and colored bars that all seem to say "this one is best." At first glance, these rankings look simple: find the model at the top, use that one. In practice, leaderboards are a lot more nuanced, and reading them well is a skill that will save you time, money, and a fair amount of frustration. This post walks through what LLM leaderboards actuall
Read More →
How to Talk to Your Local LLM on Android: Hands-Free Voice Chat with LM Studio and Ollama
If you've ever wished you could just talk to your own private AI the way you talk to Siri or Google Assistant, but without your words being uploaded to a data center somewhere, you're not alone. That's exactly the gap that local LLMs, paired with the right Android app, can fill. Running models through LM Studio or Ollama already gets you privacy and control on your desktop or laptop. The catch is that most people still interact with those models by typing at a keyboard, tethered to whatever mac
Read More →
Say Hello to Voice Mode: Now You Can Actually Talk to Your Local LLM
We're proud to introduce Voice Mode — one of the most requested features in LMSA's history, and one we've been genuinely excited to build. It's the kind of feature that changes how the whole app feels to use, and now that it's here, it's hard to imagine LMSA without it. So let's talk about it. Literally. Why We Even Wanted This Typing to an AI model is fine. It works. But there's something a little stiff about it, isn't there? You're standing in your kitchen with flour on your hands trying t
Read More →
The Ultimate Guide to Private AI Voice Chat: Using LMSA with LM Studio, Ollama, and OpenRouter
We are living in the golden age of artificial intelligence, but for many of us, the convenience of AI comes with an uncomfortable compromise: our privacy. Standard cloud-based voice assistants and AI chatbots constantly stream your data, your queries, and even your biometric voice data to remote servers. But what if you could have the fluid, hands-free experience of a smart voice assistant without sacrificing your data? What if you could talk directly to an AI running on your own hardware, in y
Read More →
How to Configure a Local AI Setup for Maximum Mobile Battery Life
You've probably tinkered with a local AI chatbot on your phone at some point. Maybe you downloaded an app that runs a small language model directly on your device. It worked - sort of. But did you notice how fast your battery percentage started dropping? How the back of your phone turned into a tiny space heater? How that "quick chat" turned into a 15% battery drain in what felt like five minutes? You're not imagining things. Running large language models (LLMs) on mobile devices is brutally e
Read More →