█▀█ █▀▀ ▄▀█ █▀▄ █▀▄▀█ █▀█ █▀█ █▀▀ █▀▄ ██▄ █▀█ █▄▀ █ ▀ █ █▄█ █▀▄ ██▄ Download Llama C++ w TurboQuant: https://github.com/TheTom/turboquant_plus#build-llamacpp-with-turboquant Qwen3.6: https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF TurboQuant: https://research.google/blog/turboquant-redefining-ai-efficiency-with-extreme-compression/ Most developers are settling for mediocre local AI performance because they are too afraid to touch the source code. This video breaks down how to ditch the bloated wrappers and run the purest Llama CPP setup with cutting edge Turbo Quant technology. Key Takeaways: - Why LM Studio and Ollama might be the cause of your timeout errors. - How to build Llama CPP from source using Tom's Turbo Quant branch. - Optimising KV cache to fit larger models like Qwen 3.6 into limited VRAM. - Connecting your local server to VS Code and OpenClaw for a pro workflow. - Managing context windows and asymmetric quantisation for peak performance. Work with me: https://samuelgregory.co.uk --- Support the content: https://www.patreon.com/0x5am5 Twitter: @0x5am5 ▀█▀ █▀█ █▀█ █ █▀ █ █▄█ █▄█ █▄ ▄█ Kilo: https://samuelgregory.co.uk/kilo-code Replit (Favourite Vibe Code Tool) : https://samuelgregory.co.uk/replit Perplexity (deep research): https://samuelgregory.co.uk/perplexity Claude Code: https://claude.ai/api/referral/jZ9vnMedyQ&v=p-CzOtUYEyA Warp Terminal: https://samuelgregory.co.uk/warp ⚒️ more at https://samuelgregory.co.uk/tools █▀▀ █▀▀ █▀▀█ ▀█░█▀ ░▀░ █▀▀ █▀▀ █▀▀ ▀▀█ █▀▀ █▄▄▀ ░█▄█░ ▀█▀ █░░ █▀▀ ▀▀█ ▀▀▀ ▀▀▀ ▀░▀▀ ░░▀░░ ▀▀▀ ▀▀▀ ▀▀▀ ▀▀▀ Domain Names: https://samuelgregory.co.uk/namecheap Hosting: https://www.hostg.xyz/aff_c?offer_id=6&aff_id=130549 Online Storage ($200 credit): https://samuelgregory.co.uk/digital-ocean ⚒️ more at https://samuelgregory.co.uk/tools █▀▀▀ █▀▀ █▀▀█ █▀▀█ █░▀█ █▀▀ █▄▄█ █▄▄▀ ▀▀▀▀ ▀▀▀ ▀░░▀ ▀░▀▀ Sony A7c II: https://amzn.to/40qaYEJ Lens Sigma 16-28mm: https://amzn.to/3IaDzqx Microphone Samson QU2: https://amzn.to/3TkshCE Macbook Pro M1 Max: https://amzn.to/48736M6 █▄▄ █▀█ █▀█ █▄▀ █▀ █▄█ █▄█ █▄█ █ █ ▄█ The Full Stack Agency: https://flowst8.dev/store Lingo: Agile: https://thefullstackagency.gumroad.com/l/agile-lingo Lingo: Startup: https://thefullstackagency.gumroad.com/l/startup-lingo ▀▀█▀▀ ░▀░ █▀▄▀█ █▀▀ █▀▀ ▀▀█▀▀ █▀▀█ █▀▄▀█ █▀▀█ █▀▀ ░░█░░ ▀█▀ █░▀░█ █▀▀ ▀▀█ ░░█░░ █▄▄█ █░▀░█ █░░█ ▀▀█ ░░▀░░ ▀▀▀ ▀░░░▀ ▀▀▀ ▀▀▀ ░░▀░░ ▀░░▀ ▀░░░▀ █▀▀▀ ▀▀▀ 00:00 getting local AI running is easier than you think. 00:28 LM Studio and Ollama is Llama C++ under the hood 00:55 what is TurboQuant? 01:52 downloading Llama++ with TurboQuant. 03:47 building the application files. 04:48 deciding on a model and what to download (Qwen3.6) 06:06 a lesson on quantization amounts and model sizes. 09:29 running the model locally and understanding different parameters 10:07 asymmetric KV quantization. 11:13 context length is very important. 14:10 running the model on a local server. 14:50 coding with the model with Kilo code 17:23 setting it up with OpenClaw. #LocalLLM #LlamaCPP #AIWorkflow false 2026-05-21 09:02:20 20260421 21 Education G:\jelly\meta\library\63\63355c1da1fc4fea0c3641ed84d495b8\poster.png Samuel Gregory bin_data bin_data 4 eng progressive False False png png 1280 720 16:9 16:9 90000 progressive False False