You don't need an expensive GPU to run a local LLM that actually works
…So, I decided to launch two LLMs on the hardware, Qwen3:4b and Qwen2.5-coder:7b. These are small models but have proven useful in handling submitted queries. Turns out, I…
Search
Tracked topic
Qwen3
Qwen3 is an AI model family developed by Alibaba, released as a set of large language models for natural-language tasks.
I fine-tuned a 7B model to write my Home Assistant automations, and it actually works
…Using the Lenovo ThinkStation PGX (the same device I used for Qwen3 Coder Next ), I fine-tuned Qwen2.5-Coder-7B-Instruct, a 7-billion-parameter open-weight model, to actually understand…
OpenClaw promised a self-hosted AI assistant I could actually leave running, but Hermes Agent is the one that delivers it
…I set it up on my Mac, pointed it at Qwen3.6-35B-A3B running on the Lenovo ThinkStation PGX , and built a daily tech news workflow that pulls from a handful…
Ubuntu just showed Microsoft how to add AI without the mess
…Related I replaced ChatGPT and Claude with this powerful local LLM and saved over $20 a month while gaining full control Qwen3.6 runs on my old GPU and does what ChatGPT…
Google Home and Alexa can't do what I built in Home Assistant, and that's the whole point
…spare rig for hosting LLMs, anyway – one that harnesses a mere GTX 1080 to run Qwen3 (8B) via Ollama . Likewise, I run faster-whisper (speech-to-text) and Piper (text-to-speech…
Google's Gemma 4 isn't the smartest local LLM I've run, but it's the one I reach for most
…Where the 31B would pull ahead is on harder coding tasks and complex multi-step reasoning, but those are also the tasks where I'm more likely to reach for Qwen3 Coder…
Local LLMs changed how I use Home Assistant, and now my smart devices actually listen
…Specifically, I rely on the Qwen3 (8B) model, as it understands most of my queries without hallucinating the answers, and I’ve used the Ollama integration built into HASS to pair them…
I use this local AI tool to turn boring documents into cool narrations
…Related I replaced ChatGPT and Claude with this powerful local LLM and saved over $20 a month while gaining full control Qwen3.6 runs on my old GPU and does what ChatGPT…
I've been running some of the biggest open-weight LLMs for free on Nvidia's cloud
…Kimi K2 Thinking, Qwen3-Coder-480B, DeepSeek V3.2, Llama 4 Maverick, Mistral Large 3, Devstral 2, ByteDance's Seed-OSS, and Google's Gemma 3 family are all in there too…
I rebuilt my VS Code setup from scratch this year, and it's the fastest it's ever been
…Plus, the likes of Gemma4-26B-A4B and Qwen3.6-35B-A3B can hold their own against typical cloud-based models, and they mesh incredibly well with VS Code for everything from…