local LLM
8 stories tagged local LLM.
Qwen3.8-27B Fits a 12GB Card, Except When It Can See
A 27B multimodal model now ships as an 11.8GB download, but the byte math shows a 12GB GPU has almost no context left once images load.
Qwen3.8-Flash-Next Puts 180B Parameters on Laptop Hardware
Qwen3.8-Flash-Next Puts 180B Parameters on Laptop Hardware
Qwen3.8-Flash-Next uses a 51B engram lookup table in system RAM to run 180B parameters on modest hardware. Here's what the architecture actually means.
Self-Hosted AI Tools That Replace Paid SaaS
Self-Hosted AI Tools That Replace Paid SaaS
Ten open-source AI tools—from Tesseract OCR to OpenHands—that run locally, protect your data, and eliminate SaaS subscriptions. Here's what works and what doesn't.
July 2026 GitHub Trending: What Developers Actually Built
July 2026 GitHub Trending: What Developers Actually Built
35 projects topped GitHub's trending list in July 2026. The patterns they form say more about developer priorities than any roadmap ever could.
Nvidia's DGX Station GB300: Desktop AI Agent Testing
Nvidia's DGX Station GB300: Desktop AI Agent Testing
Alex Ziskind tests Nvidia's GB300-powered DGX Station desktop, running 128 simultaneous AI agents. Here's what the numbers actually reveal about on-premise AI.
35 Trending GitHub Projects Reshaping AI Dev
35 Trending GitHub Projects Reshaping AI Dev
From hallucinating browsers to retro Rust IDEs, GitHub's trending list this week is a real-time snapshot of where AI tooling is actually heading.
Perplexica: Free AI Search Engine That Runs on Your Laptop
Perplexica: Free AI Search Engine That Runs on Your Laptop
Perplexica is an open-source alternative to Perplexity that runs locally. But do you actually want an AI search engine that never leaves your machine?
AnythingLLM Wants to Replace Your Entire Local AI Stack
AnythingLLM Wants to Replace Your Entire Local AI Stack
AnythingLLM promises to consolidate Ollama, LangChain, and vector databases into one workspace. Does it solve local LLM workflow problems or just hide them?