✕ Clear all filters
25 articles

📰 Dev.to · David

25 articles · Updated every 3 hours · View all reads

All Articles 76,672Blog Posts 102,400Tech Tutorials 18,670Research Papers 16,245News 13,256 ⚡ AI Lessons
How to Run Qwen 3.6 Locally - 27B Dense, 35B MoE, and Coding Variants Setup Guide
Dev.to · David 1mo ago
How to Run Qwen 3.6 Locally - 27B Dense, 35B MoE, and Coding Variants Setup Guide
Complete step-by-step guide to running Qwen 3.6 locally - 27B dense, 35B MoE, NVFP4, BF16, hardware requirements, GGUF download links.
Read article → + Playlist
Abliterated Models Guide - Qwen 3.6, Gemma 4 Heretic, Llama 3.1 Uncensored Download Links
Dev.to · David 1mo ago
Abliterated Models Guide - Qwen 3.6, Gemma 4 Heretic, Llama 3.1 Uncensored Download Links
What abliteration is, which models are available in 2026, where to download, how to run them locally with one click.
Read article → + Playlist
Anthropic is Rationing Claude Code on Pro — Here's a Local Alternative
Dev.to · David 1mo ago
Anthropic is Rationing Claude Code on Pro — Here's a Local Alternative
Earlier this week, Anthropic ran a quiet test: a small slice (~2%) of new Pro plan subscribers found...
Read article → + Playlist
qwen3.6-27b scores 77.2% on SWE-bench. the dense model is winning against MoE.
Dev.to · David 1mo ago
qwen3.6-27b scores 77.2% on SWE-bench. the dense model is winning against MoE.
When Alibaba released Qwen3.6-35B-A3B, the MoE (Mixture of Experts) design stole all the headlines....
Read article → + Playlist
how to run qwen3.6-27b locally — the dense 27B that beats the 35B MoE on coding
Dev.to · David 1mo ago
how to run qwen3.6-27b locally — the dense 27B that beats the 35B MoE on coding
Alibaba just dropped Qwen3.6-27B, a 27-billion parameter dense model that scores 77.2% on SWE-bench...
Read article → + Playlist
How to Run GLM 4.7 Flash Locally with Ollama — 30B Quality at 3B Speed
Dev.to · David 1mo ago
How to Run GLM 4.7 Flash Locally with Ollama — 30B Quality at 3B Speed
ZhipuAI quietly dropped GLM 4.7 Flash and it's been blowing up — 830K+ downloads on HuggingFace,...
Read article → + Playlist
France is ditching Windows for Linux. your AI should be next.
Dev.to · David 1mo ago
France is ditching Windows for Linux. your AI should be next.
France just announced they're migrating government systems from Windows to Linux to reduce dependence...
Read article → + Playlist
i cancelled ChatGPT, Midjourney, and Copilot. here's the $0/month stack that replaced all three.
Dev.to · David 1mo ago
i cancelled ChatGPT, Midjourney, and Copilot. here's the $0/month stack that replaced all three.
ChatGPT Plus: $20/month. Midjourney: $10/month. GitHub Copilot: $10/month. That's $480/year for AI...
Read article → + Playlist
the FBI can read your ChatGPT history. they can't read mine.
Dev.to · David 1mo ago
the FBI can read your ChatGPT history. they can't read mine.
The FBI just retrieved deleted Signal messages through iPhone notification data. That was supposed to...
Read article → + Playlist
OpenAI just mass-unsubscribed paying users — the case for running AI locally
Dev.to · David 1mo ago
OpenAI just mass-unsubscribed paying users — the case for running AI locally
Yesterday, thousands of ChatGPT Plus and Pro subscribers woke up to find their paid accounts...
Read article → + Playlist
i generated AI video on a GTX 1660. here's what it actually takes.
Dev.to · David 1mo ago
i generated AI video on a GTX 1660. here's what it actually takes.
A few weeks ago, generating video from a single image required either a cloud API with per-second...
Read article → + Playlist
image-to-image with local AI models — which model for what, and how denoise strength actually works
Dev.to · David 1mo ago
image-to-image with local AI models — which model for what, and how denoise strength actually works
Most local AI image tools give you text-to-image and call it done. You type a prompt, get an image,...
Read article → + Playlist
GLM 5.1 just dropped — 754B open-weight MoE model under MIT license. here's how to run it
Dev.to · David 1mo ago
GLM 5.1 just dropped — 754B open-weight MoE model under MIT license. here's how to run it
GLM 5.1 dropped two days ago. 754 billion parameters, Mixture-of-Experts architecture, MIT license....
Read article → + Playlist
v2.3.0 — ComfyUI plug & play, image-to-video on 6 GB VRAM, and uncensored image gen in a local AI desktop app
Dev.to · David 1mo ago
v2.3.0 — ComfyUI plug & play, image-to-video on 6 GB VRAM, and uncensored image gen in a local AI desktop app
Today we're releasing v2.3.0 of Locally Uncensored — an open-source desktop app for running AI...
Read article → + Playlist
your local AI agent shouldn't care which model you run
Dev.to · David 2mo ago
your local AI agent shouldn't care which model you run
your local AI agent shouldn't care which model you run Most local AI apps that offer agent...
Read article → + Playlist
OpenAI's pricing is about to change — here's why local AI matters more than ever
Dev.to · David 2mo ago
OpenAI's pricing is about to change — here's why local AI matters more than ever
OpenAI just had one of its biggest days ever. Free tier gets GPT-4o and image generation. A new...
Read article → + Playlist
OpenAI's trust problem is getting worse — here's your local plan B
Dev.to · David 2mo ago
OpenAI's trust problem is getting worse — here's your local plan B
This week, a massive New Yorker investigation landed with 1400+ upvotes on Hacker News and 30,000+ on...
Read article → + Playlist
VRAM Is the New RAM — A Practical Guide to Running Large Language Models on Consumer GPUs
Dev.to · David 2mo ago
VRAM Is the New RAM — A Practical Guide to Running Large Language Models on Consumer GPUs
Your GPU has 8 GB of VRAM. The model you want to run needs 14 GB. What now? This is the most common...
Read article → + Playlist
We Just Shipped a Coding Agent Inside a Desktop AI App — Here's How It Works
Dev.to · David 2mo ago
We Just Shipped a Coding Agent Inside a Desktop AI App — Here's How It Works
I've been building Locally Uncensored, an open-source desktop app for running AI locally. Today we...
Read article → + Playlist
Anthropic Is Tightening the Screws — First-Party Harness Access Now Blocked Too
Dev.to · David 2mo ago
Anthropic Is Tightening the Screws — First-Party Harness Access Now Blocked Too
Yesterday, Anthropic cut off Claude Pro and Max subscriptions from working with third-party tools...
Read article → + Playlist
Anthropic Just Restricted Third-Party Claude Access — Why Running AI Locally Is Your Insurance Policy
Dev.to · David 2mo ago
Anthropic Just Restricted Third-Party Claude Access — Why Running AI Locally Is Your Insurance Policy
API dependency is a recurring theme in the AI world, and today it hit home for thousands of...
Read article → + Playlist
Making Local LLMs Use Tools — Even When They Weren't Designed For It
Dev.to · David 2mo ago
Making Local LLMs Use Tools — Even When They Weren't Designed For It
Most local LLM UIs let you chat. Some let you tweak parameters. But what if the model could actually...
Read article → + Playlist
Building Real-Time A/B Model Comparison with Parallel Async Streams in TypeScript
Dev.to · David 2mo ago
Building Real-Time A/B Model Comparison with Parallel Async Streams in TypeScript
Ever wanted to pit two LLMs against each other with the exact same prompt and see who wins — in real...
Read article → + Playlist
Locally Uncensored v1.5.5 — Zero-Config AI Models, VRAM Detection & Production-Ready Desktop App
Dev.to · David 2mo ago
Locally Uncensored v1.5.5 — Zero-Config AI Models, VRAM Detection & Production-Ready Desktop App
We just shipped v1.5.5 of Locally Uncensored — the open-source, local-first AI desktop app for Chat +...
Read article → + Playlist