Uploaded October 2026 | Updated November 2026, 2 days ago
Run a 125B AI Model on Your Gaming PC! π€― Strata + Qwen3.8-Flash-Next Tutorial
What if you could run a 125-billion-parameter AI model on your own PC without paying for cloud AI subscriptions? π In this tutorial, we explore Strata, an open-source tool designed to run Qwen3.8-Flash-Next locally by combining your GPU, system RAM, CPU, and SSD.
π PROJECT LINKS
β’ Strata GitHub: github.com/Niko1221/Strata
β’ Qwen3.8-Flash-Next on Hugging Face: huggingface.co/Qwen/Qwen3.8-Flash-Next
π What You'll Learn in This Video
β What Strata is and how it runs large AI models locally
β How Qwen3.8-Flash-Next can run on consumer gaming hardware
β How GPU VRAM, system RAM, CPU, and SSD work together
β How model quantization balances AI quality, memory usage, and speed
β How to install Strata on Windows or Linux
β How to choose a model variant based on your available RAM
β How to chat with your local AI through a browser
β How to connect local AI to coding assistants and other applications
β How speculative decoding can improve generation speed
β How to monitor performance and troubleshoot common problems
π₯οΈ What PC Hardware Do You Need?
According to the tutorial, the recommended starting point includes:
β’ GPU: 12 GB VRAM or more
β’ System RAM: 32 GB or more
β’ Storage: Approximately 80 GB of free disk space
β’ Operating system: Windows 10/11 or Linux
β’ Storage recommendation: An SSD for faster loading
β‘ How Does Strata Make This Possible?
Instead of relying exclusively on GPU memory, Strata distributes the workload across multiple parts of your computer.
π§ GPU: Keeps frequently used model components close to the processor.
πΎ RAM: Holds model components that cannot fit entirely in VRAM.
βοΈ CPU: Helps process work that is not handled entirely by the GPU.
π SSD: Provides storage for model files and supporting data.
π Why Run AI Locally?
Running AI on your own hardware can offer several advantages:
β’ Greater control over your AI environment
β’ Reduced dependence on cloud services
β’ No per-token cloud API charges when using the local model
β’ The ability to experiment with coding assistants and AI applications
β’ More privacy when prompts and processing remain on your own machine.
π¬ QUESTION OF THE DAY: Would you run a 125B-parameter AI model on your own gaming PC? Tell us your GPU, VRAM, and system RAM in the comments!
π If you enjoy practical tutorials about local AI, open-source models, and AI infrastructure, please LIKE the video, SUBSCRIBE to the channel, and turn on notifications for more tutorials.
πΈ Buy me a coffee :
buymeacoffee.com/liv4it
πΈ Support channel & make donation :
paypal.me/aminenina/10
πΈ Subscribe for more videos :
YouTube: youtube.com/user/aminosninatos
πΈ Follow me On Social Media
Facebook : facebook.com/aminosninatos
***********************************************************************
πΈπ€ The Story of Clef Cloudflare's Decision Model
youtu.be/DfozliZeG1o
πΈπ€ The Story of JEV: The New AI Model That Thinks Differently
youtu.be/u1FadbazpB8
πΈπ The Evolution of DeepSeek LLMs: From V1 to V4
youtu.be/ZKTRzfs2qPk
πΈπ The Story of Qwen: How Alibaba Built One of the World's Most Popular Open-Source AI Models
youtu.be/F0c1Rcr7JpU
πΈπ Run Large Language Models Locally on Your Own Computer β Beginner Friendly Tutorial
youtu.be/jOJ5q1k6FSk
πΈπ€ The Story of AI Agents β Beginner-Friendly Tutorial
youtu.be/qbuBp6dMi54
πΈπ§ Mixture of Experts (MoE): How the Next Generation of LLMs Scale Smarter
youtu.be/82LHAxbHQYM
πΈπ Fine-Tuning & LoRA Explained β A Complete Beginner's Guide
youtu.be/7YtBTManl1U
πΈπ¦ LLM Quantization Explained: FP32, FP16, INT8, INT4, GPTQ, AWQ & GGUF
youtu.be/37g8S71LfmQ
πΈπ The Unsloth Company Story: How Two Brothers Are Making AI Fine-Tuning Faster
youtu.be/Rv0SOk_0Rc4
πΈπ LLM Families Explained: The Complete Guide to Modern AI Models (Open Source vs Proprietary)
youtu.be/lUFx2VPapKs
πΈπ LLM Sampling Explained: Temperature vs Top-K vs Top-P (Visual Guide for Beginners)
youtu.be/j2ZGvE7FvvU
πΈβ©οΈ What does the --jinja flag do in llama.cpp? Complete Beginner's Guide
youtu.be/niEkHqxzgZQ
πΈπ MTP GGUF Models Explained | What They Are & How to Use Them with llama-server
youtu.be/LV_30Rufu2s
πΈπ§ GGUF File Names Explained for Beginners | Learn Q4_K_M, IQ, UD, QAT, MoE & More!
youtu.be/yzMENYCtPxg
πΈ π¦ llama-server Command Line Overview | Complete Guide to Every Option in llama.cpp
youtu.be/N-Mc7_3z3uU
πΈ π¦ Run Large Language Models on Your Computer Using llama.cpp | Complete Beginner's Guide
youtu.be/up-iIZNj3mw
πΈ Download Hugging Face Models FAST! π HF CLI + Xet Storage Engine (Complete 2026 Guide)
youtu.be/8uDbEy2VKKs
***********************************************************************
#strata #qwen #ai
Run a 125B AI Model on Your Gaming PC! π€― Strata + Qwen3.8-Flash-Next Tutorial
What if you could run a 125-billion-parameter AI model on your own PC without paying for cloud AI subscriptions? π In this tutorial, we explore Strata, an open-source tool designed to run Qwen3.8-Flash-Next locally by combining your GPU, system RAM, CPU, and SSD.
π PROJECT LINKS
β’ Strata GitHub: github.com/Niko1221/Strata
β’ Qwen3.8-Flash-Next on Hugging Face: huggingface.co/Qwen/Qwen3.8-Flash-Next
π What You'll Learn in This Video
β What Strata is and how it runs large AI models locally
β How Qwen3.8-Flash-Next can run on consumer gaming hardware
β How GPU VRAM, system RAM, CPU, and SSD work together
β How model quantization balances AI quality, memory usage, and speed
β How to install Strata on Windows or Linux
β How to choose a model variant based on your available RAM
β How to chat with your local AI through a browser
β How to connect local AI to coding assistants and other applications
β How speculative decoding can improve generation speed
β How to monitor performance and troubleshoot common problems
π₯οΈ What PC Hardware Do You Need?
According to the tutorial, the recommended starting point includes:
β’ GPU: 12 GB VRAM or more
β’ System RAM: 32 GB or more
β’ Storage: Approximately 80 GB of free disk space
β’ Operating system: Windows 10/11 or Linux
β’ Storage recommendation: An SSD for faster loading
β‘ How Does Strata Make This Possible?
Instead of relying exclusively on GPU memory, Strata distributes the workload across multiple parts of your computer.
π§ GPU: Keeps frequently used model components close to the processor.
πΎ RAM: Holds model components that cannot fit entirely in VRAM.
βοΈ CPU: Helps process work that is not handled entirely by the GPU.
π SSD: Provides storage for model files and supporting data.
π Why Run AI Locally?
Running AI on your own hardware can offer several advantages:
β’ Greater control over your AI environment
β’ Reduced dependence on cloud services
β’ No per-token cloud API charges when using the local model
β’ The ability to experiment with coding assistants and AI applications
β’ More privacy when prompts and processing remain on your own machine.
π¬ QUESTION OF THE DAY: Would you run a 125B-parameter AI model on your own gaming PC? Tell us your GPU, VRAM, and system RAM in the comments!
π If you enjoy practical tutorials about local AI, open-source models, and AI infrastructure, please LIKE the video, SUBSCRIBE to the channel, and turn on notifications for more tutorials.
πΈ Buy me a coffee :
buymeacoffee.com/liv4it
πΈ Support channel & make donation :
paypal.me/aminenina/10
πΈ Subscribe for more videos :
YouTube: youtube.com/user/aminosninatos
πΈ Follow me On Social Media
Facebook : facebook.com/aminosninatos
***********************************************************************
πΈπ€ The Story of Clef Cloudflare's Decision Model
youtu.be/DfozliZeG1o
πΈπ€ The Story of JEV: The New AI Model That Thinks Differently
youtu.be/u1FadbazpB8
πΈπ The Evolution of DeepSeek LLMs: From V1 to V4
youtu.be/ZKTRzfs2qPk
πΈπ The Story of Qwen: How Alibaba Built One of the World's Most Popular Open-Source AI Models
youtu.be/F0c1Rcr7JpU
πΈπ Run Large Language Models Locally on Your Own Computer β Beginner Friendly Tutorial
youtu.be/jOJ5q1k6FSk
πΈπ€ The Story of AI Agents β Beginner-Friendly Tutorial
youtu.be/qbuBp6dMi54
πΈπ§ Mixture of Experts (MoE): How the Next Generation of LLMs Scale Smarter
youtu.be/82LHAxbHQYM
πΈπ Fine-Tuning & LoRA Explained β A Complete Beginner's Guide
youtu.be/7YtBTManl1U
πΈπ¦ LLM Quantization Explained: FP32, FP16, INT8, INT4, GPTQ, AWQ & GGUF
youtu.be/37g8S71LfmQ
πΈπ The Unsloth Company Story: How Two Brothers Are Making AI Fine-Tuning Faster
youtu.be/Rv0SOk_0Rc4
πΈπ LLM Families Explained: The Complete Guide to Modern AI Models (Open Source vs Proprietary)
youtu.be/lUFx2VPapKs
πΈπ LLM Sampling Explained: Temperature vs Top-K vs Top-P (Visual Guide for Beginners)
youtu.be/j2ZGvE7FvvU
πΈβ©οΈ What does the --jinja flag do in llama.cpp? Complete Beginner's Guide
youtu.be/niEkHqxzgZQ
πΈπ MTP GGUF Models Explained | What They Are & How to Use Them with llama-server
youtu.be/LV_30Rufu2s
πΈπ§ GGUF File Names Explained for Beginners | Learn Q4_K_M, IQ, UD, QAT, MoE & More!
youtu.be/yzMENYCtPxg
πΈ π¦ llama-server Command Line Overview | Complete Guide to Every Option in llama.cpp
youtu.be/N-Mc7_3z3uU
πΈ π¦ Run Large Language Models on Your Computer Using llama.cpp | Complete Beginner's Guide
youtu.be/up-iIZNj3mw
πΈ Download Hugging Face Models FAST! π HF CLI + Xet Storage Engine (Complete 2026 Guide)
youtu.be/8uDbEy2VKKs
***********************************************************************
#strata #qwen #ai










