LNLifeHack Nexusinlifehacknexus.hashnode.dev·2d ago · 14 min readThe Local DeepSeek-R1 Reasoning Blueprint: Running 14B & 32B Models on Consumer GPUs for $0 (VRAM Math & Setup) ⚡ Benchmarking Summary & Local Hardware Telemetry: The release of DeepSeek-R1 has shattered the proprietary AI monopoly. By utilizing Large-Scale Reinforcement Learning (RL) with test-time compute, o00
DBDamiano Biandaindamianobianda.hashnode.dev·2d ago · 4 min readThe letter you can't paste into a chatbot: explaining official mail with a fully local 1B modelA Zahlungsbefehl is not the kind of letter you photograph and upload somewhere. It is a formal payment order from the Swiss debt-collection office: your full name, your address, the creditor, the amou00
RDRONI DASinsystemdesignacademy.hashnode.dev·4d ago · 12 min readThere is no 4B Qwen 3.8. The smallest open model is 27B, and here is what it took to run it on one rented GPU.Where is the Qwen 3.8 you can run on a laptop? I went looking for a 2B or 4B version, the kind that fits next to your browser tabs, and there is none. The Hugging Face listing for the Qwen team shows 01D
KHKhadim Hussaininkhadimhussain0.hashnode.dev·6d ago · 7 min readFine-tune gpt-oss-20b with Unsloth and run it in OllamaOriginally published on khadim.tech. In short: gpt-oss-20b fine-tunes with QLoRA on a single consumer GPU (Unsloth puts it at about 14 GB of VRAM). Shipping it is where the chat template matters: gpt-11M
ISIbrahim Shaikhinibmshaikh.hashnode.dev·6d ago · 4 min readRun a local coding agent with Ollama + Qwen 3 using OpenPilotI wanted something like Cursor that was open source and let me use whatever model I wanted, including ones running on my own machine. I couldn't find one, so I built OpenPilot. It's a desktop app (Ele00
HSHaithem Slimiinnightthoughts.me·Oct 9 · 15 min readRunning LLMs Locally: How to Pick the Right Tool and Model for Your MachineBefore you start: what local LLMs can and can't do Running a model on your own machine buys you privacy, offline access, no rate limits, and no per-token bill. It does not buy you frontier-level intel11A
MCMateusz Czernekinmateusz-czernek.pl·Oct 8 · 7 min readExamBuddy: First Steps in AI IntegrationA while ago, I created an application to help my wife prepare for exams. It allows users to create exams with sets of questions and answers, take those exams, and save the results. Recently, I decided02N
AArchestackinarchestack.hashnode.dev·Oct 9 · 2 min readOnly 10 of 89 AI starter templates work with local models out of the boxIf you want to build an AI app that runs on your own models, the starter you fork matters. We track 89 open-source starter templates for AI apps, and each entry records what the README says about mode00
MSMIG serversinmigservers.hashnode.dev·Oct 9 · 11 min readRun Ollama with GPU on Ubuntu Using Docker and Open WebUIRunning large language models locally gives developers more control over their AI environment. With Ollama, Docker, and Open WebUI, you can set up a self-hosted AI chatbot on an Ubuntu server with NVI00
HSHaithem Slimiinnightthoughts.me·Oct 7 · 16 min readAgent Orchestration with OpenClaw: A Multi-Agent Blogging System1. Purpose and Design Principles This guide teaches multi-agent orchestration through a concrete, end-to-end example: an autonomous blogging system. Most guides about AI agents show a single agent cal10
