Tag

#local-ai

91 posts0 followers

Explore Hashnode

Alternatives

Haithem SlimiOct 14 · 13 min read

The Memory Wall: How NVIDIA’s RTX Spark Changes the AI Bottleneck

Introduction When people talk about AI hardware, the conversation usually centers on compute. How many teraflops can a chip push? How many operations per second? Faster chips sound like faster AI. But

2 nightthoughts.me

Haithem SlimiOct 13 · 6 min read

The Future Is Both

New to the jargon? Start with the glossary → Most AI systems today pick a side. They run entirely local or entirely cloud. That's a design choice, not a law of nature. The choice made sense when loca

nightthoughts.me

Sanjay JanaOct 11 · 5 min read

Building Solomon: a private, local-first AI assistant

Why we built Solomon Solomon is an AI assistant that chats, searches the web with citations, reads your files and draws images, and most of it runs on our own machines. We built it to see how far a pr

codedecoder.hashnode.dev

Mihai_LeanZeroOct 8 · 53 min read

Qwen3.8 Flash vs Max Prime: Forge app benchmark

Qwen3.8 Flash vs Max Prime is the oddest result inside one model family on our boards. The far cheaper Flash beat Qwen3.8 Max Prime on Forge 1.0, an Atlassian Forge app built with no internet, 0.7961

leanzero.hashnode.dev

Haithem SlimiOct 7 · 8 min read

Who Actually Saves Money?

Who Actually Saves Money? New to the jargon? Start with the glossary → "Local AI is free." You'll see that line in forum threads, in YouTube comments, in the pitch for every new tool that runs on you

1 nightthoughts.me

Dragos RouaOct 8 · 2 min read

[ Video ] Running Liquid AI LFM V2.5 on my 16 GB MacBookPro

This is our fourth video in the series: Local AI – models that you can actually run on an entry level machine, like a 16GB MacBookPro. This time we’re testing LFM 2.5 3B, a 3 billion model from Liquid

dragosroua.hashnode.dev

Mihai_LeanZeroOct 5 · 72 min read

Claude Sonnet 5.5 vs Opus 5.5 and GPT-6.1 Sol: the generalist and the specialist

Claude Sonnet 5.5 vs Opus 5.5 and GPT-6.1 Sol: the generalist and the specialist Correction, 10 October 2026: a review of Forge 1.0's scoring on 9 October found faults that make Claude Sonnet 5.5's 0

leanzero.hashnode.dev

Haithem SlimiOct 4 · 6 min read

Bigger Isn't Always Smarter

New to the jargon? Start with the plain-English glossary. For years, the rule was simple: bigger AI meant smarter AI. More parameters, more brainpower. Every new model was just the last one, scaled u

3 nightthoughts.me

Haithem SlimiOct 4 · 5 min read

How a Laptop Learned to Run a Giant

New to the jargon? Start with the glossary → A 70-billion-parameter model is roughly 140 GB of data. A mid-range gaming laptop has between 8 and 16 GB of video memory. That's like trying to pour a sw

1 nightthoughts.me

Dragos RouaOct 3 · 4 min read

[ Video ] How To Set Up Local AI on a 16GB MacBook

One of my YouTube subscribers asked, in a comment, how to set up a 16GB M1 MacBook Pro so it runs models in a more comfortable way, not necessarily in the terminal. This came as a reaction to my local

dragosroua.hashnode.dev

Search Hashnode

Explore Hashnode

Trending tags this week

The Memory Wall: How NVIDIA’s RTX Spark Changes the AI Bottleneck

The Future Is Both

Building Solomon: a private, local-first AI assistant

Qwen3.8 Flash vs Max Prime: Forge app benchmark

Who Actually Saves Money?

[ Video ] Running Liquid AI LFM V2.5 on my 16 GB MacBookPro

Claude Sonnet 5.5 vs Opus 5.5 and GPT-6.1 Sol: the generalist and the specialist

Bigger Isn't Always Smarter

How a Laptop Learned to Run a Giant

[ Video ] How To Set Up Local AI on a 16GB MacBook