Local LLM on Two Used GPUs: A Practical AI Machine
Description
Used parts, turned into a practical AI machine. Two used AMD graphics cards, an RX 6900 XT and an RX 6800, run a 35-billion-parameter local LLM with a 96k context and write real code at about 90-112 tokens a second. Full guide, every command copy-paste ready, on Vibe Garage: https://vibegarage.neozonesproductions.com/learn.html?p=ZEzo6OJ6bm-dv68iTmQ-Kw Chapters: 0:00 Used parts, practical AI machine 0:25 Why this setup 0:46 Step 1: the rig 1:03 Step 2: why two cards 2:16 Step 3: the model 2:50 Step 4: the command 3:30 Is it practical? The proof 4:13 Bigger context just slows it down 4:33 The honest limits 5:01 Recap and the full guide Launch command (llama.cpp build b11871, Vulkan): llama-server -m Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf -ngl 999 -sm layer -ts 1,1 -c 98304 -fa on --spec-type dr
22:54Embrace the Coming AI Revolution with Safe Local AI!Level1Techs69.2K views
25:14You Don't need to use Cloud AI! Switchyard and Nemotron 3.5 LightningLevel1Techs146K views
20:38AI Doesn't Have to be Giant Data Centers!Level1Techs22.3K views
14:31How To Run Private & Uncensored LLMs Offline | Dolphin Llama 3Global Science Network1M views
22:25Running Gemma 4 Local AIExplainingComputers126K views
13:22Set up a Local AI like ChatGPT on your own machine!Dave's Garage377K views
42:58Shawn Mills – Self Hosted AI in Your Business – 14:45 – 15:30Jack Spirko428 views
2:03Gemma 4 on the iPhone (local AI, no internet required)NetworkChuck892K views
10:49Running AI Agents Locally = Safe...? Think AgainDaniel Jindoo 71.2K views
3:51Run your own AI (but private)CodeWithHarry170K views
4:18OpenAI's nightmare: Deepseek R1 on a Raspberry PiJeff Geerling2.4M views
15:21Unlimited AI Agents running locally with Ollama & AnythingLLMTim Carambat243K views
10:49Is NVIDIA’s ChatRTX The Next Big Thing?Tech With Tim17.6K views
21:27Why you NEED to be running local AI models (FULL beginners guide)Alex Finn91.6K views