--- title: Qwen3.8-Flash-Next Shrunk to 58GB — 50% Fewer Experts,... description: Qwen3.8-Flash-Next is a massive Mixture-of-Experts model, but this new GSQ-RCO Coder variant from ISTA-DASLab takes a very different approach to... canonical: https://daily.dev/posts/qwen3-8-flash-next-shrunk-to-58gb-50-fewer-experts-98-7-coding-performance--860nh2pje twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Qwen3.8-Flash-Next Shrunk to 58GB — 50% Fewer Experts, 98.7% Coding Performance! | daily.dev og:description: Qwen3.8-Flash-Next is a massive Mixture-of-Experts model, but this new GSQ-RCO Coder variant from ISTA-DASLab takes a very different approach to... og:url: https://daily.dev/posts/qwen3-8-flash-next-shrunk-to-58gb-50-fewer-experts-98-7-coding-performance--860nh2pje og:image: https://api.daily.dev/og/posts/860NH2pje.png og:image:alt: Qwen3.8-Flash-Next Shrunk to 58GB — 50% Fewer Experts, 98.7% Coding Performance! og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Qwen3.8-Flash-Next Shrunk to 58GB — 50% Fewer Experts, 98.7% Coding Performance! **[Execute Automation](https://daily.dev/sources/executeautomation)** · 11 min read · 0 upvotes · 0 comments ## Summary Qwen3.8-Flash-Next is a massive Mixture-of-Experts model, but this new GSQ-RCO Coder variant from ISTA-DASLab takes a very different approach to compression. Instead of simply quantizing everything and hoping for the best, the model uses RCO — Riemannian Constrained Optimization — to selectively retain the experts that matter most for coding and agentic workloads, reducing the available expert pool from 512 experts to 256. The remaining weights are then compressed using GSQ — Gumbel-Softmax Quantization, bringing the model down to around 58.4GB in GGUF form, with roughly 29.6GB for the transformer itself. Chapters: 00:00 - Introduction 02:20 - Running QWEN3.8-FLASH-NEXT-GSQ-RCO in LM Studio 05:44 - Comparing QWEN3.8-GSQ-RCO vs QWEN3.8-Q4 for .NET Migration 08:12 - Comparing QWEN3.8-GSQ-RCO vs QWEN3.8-Q4 for SVG Image My AI related Courses for you to empower today: Learn my latest course launched this week on ZERO Code AI Tests: Automate Software Tests in Plain English: https://www.udemy.com/course/zero-code-ai-testing/?couponCode=LEARN_SEP_26 Use code: LEARN_SEP_26 for 85% OFF (limited time) My Other AI related Courses for you to empower today: To Learn more about building your own AI Agents and Testing AI Agents, follow the courses below available in Udemy with Discount coupon codes. Use coupon code : LEARN_SEP_26 🤖 AI-Driven Test Automation: Playwright, Selenium, LLMs & More https://www.udemy.com/course/ai-test-automation-selenium-playwright-llms/?couponCode=LEARN_SEP_26 🤖 https://www.udemy.com/course/genai-multi-agent-software-testing/?couponCode=LEARN_SEP_26 🤖Test AI & LLM App with DeepEval, RAGAs & more using Ollama https://www.udemy.com/course/ai-testing-deepeval-ragas-ollama/?couponCode=LEARN_SEP_26 🤖Build & Test AI Agents, ChatBot, RAG with Ollama & Local LLM https://www.udemy.com/course/build-ai-agent-chatbot-rag-langchain-local-llm/?couponCode=LEARN_SEP_26 🤖2025 - Understand ,Test ,Fine-tune AI Model with HuggingFace https://www.udemy.com/course/ai-with-huggingface/?couponCode=LEARN_SEP_26 🤖2025 - Using Generative AI in Software Automation Testing https://www.udemy.com/course/generative-ai-in-software-automation-testing/?couponCode=LEARN_SEP_26 🤖AgentQL: https://youtu.be/XzmkFSqTgtM 🌐 Local Deepseek R1 for BrowserUse - https://youtu.be/NvClPPI4sK0 🌐 Browser Use - https://youtu.be/O1GzsqJFpuI ➜ Discount coupon codes for all the courses: LEARN_SEP_26 ► [Advanced Framework development Course in Selenium C#] https://www.udemy.com/course/framework-development-with-selenium-csharp-advanced/ ► [Advanced Framework development Course in Playwright C#] https://www.udemy.com/course/framework-development-with-playwright-dotnet/ #Qwen #Qwen38 #LocalLLM #AppleSilicon #M5Max #LLM #AI #CodingAI #GGUF #AgenticAI #LocalAI #MachineLearning #ExecuteAutomation ► [Udemy] https://www.udemy.com/user/karthik-kk/ ► [XUnit with Selenium] https://www.youtube.com/playlist?list=PL6tu16kXT9Prbp7hTEb-M-luddsRJZKJ2 ► [Git Basics] https://www.youtube.com/playlist?list=PL6tu16kXT9PqIcfMOE9hX81cVOnmiM1E2 ► [SpringBoot for Testing] https://www.youtube.com/playlist?list=PL6tu16kXT9PrDr6kMGQ-CgnvCsFxrq1eS Selenium and C# ► [C# for automation testing] https://www.youtube.com/playlist?list=PL6tu16kXT9Pp3NFZgLbPZXEykeGQwxGSx ► [Selenium with C#] https://www.youtube.com/watch?v=mluLgBywW0Y&list=PL6tu16kXT9PqKSouJUV6sRVgmcKs-VCqo ► [BDD with Specflow] https://www.youtube.com/playlist?list=PL6tu16kXT9Pp3wrsaYyNRnK1QkvVv6qdI ► [BDD with Selenium] https://www.youtube.com/playlist?list=PL6tu16kXT9PrAjLHMTtttMybnV1kDpCXk ► [Selenium .NET Core] https://www.youtube.com/playlist?list=PL6tu16kXT9PqLJfuuLcvHnE61pzD8Dq9M Selenium &Java ► [Cucumber with Selenium] https://www.youtube.com/playlist?list=PL6tu16kXT9PpteusHGISu_lHcV6MbBtA6 ► [Cucumber with Selenium] https://www.youtube.com/playlist?list=PL6tu16kXT9Pqr70SZlwcmTSAfOw_0Qj3R ► [Cucumber 4 Upgrade] https://www.youtube.com/playlist?list=PL6tu16kXT9PoT4gRr5F00r1lPaTszk_-q ► [Selenium Grid] https://www.youtube.com/playlist?list=PL6tu16kXT9Po4YMQz_uEd5FN4V3UyAZi6 ► [Selenium framework development] https://www.youtube.com/playlist?list=PL6tu16kXT9Prgk2f37ozqcdZac9pSATf6 ► [Selenium 4] https://www.youtube.com/playlist?list=PL6tu16kXT9PoYFpoLR0OaDuZDjblBPxuO ► [Selenium Grid with Docker] https://www.youtube.com/playlist?list=PL6tu16kXT9PrgjktYZJ9-ISDTEimjjxv7 ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- [View this post on daily.dev](https://daily.dev/posts/qwen3-8-flash-next-shrunk-to-58gb-50-fewer-experts-98-7-coding-performance--860nh2pje) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Qwen3.8-Flash-Next Shrunk to 58GB — 50% Fewer Experts, 98.7% Coding Performance!","url":"https://daily.dev/posts/qwen3-8-flash-next-shrunk-to-58gb-50-fewer-experts-98-7-coding-performance--860nh2pje","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/qwen3-8-flash-next-shrunk-to-58gb-50-fewer-experts-98-7-coding-performance--860nh2pje"},"datePublished":"2026-10-01T13:08:14.442Z","dateModified":"2026-10-01T14:55:19.147Z","description":"Qwen3.8-Flash-Next is a massive Mixture-of-Experts model, but this new GSQ-RCO Coder variant from ISTA-DASLab takes a very different approach to...","image":"https://i.ytimg.com/vi/gtYdl3m5KMQ/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/gtYdl3m5KMQ/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Execute Automation","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Execute Automation","logo":"https://media.daily.dev/image/upload/s--Uh-EE9Cf--/f_auto,q_auto/v1780213688/logos/executeautomation?_a=BAMAMiWQ0","url":"https://daily.dev/sources/executeautomation"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/qwen3-8-flash-next-shrunk-to-58gb-50-fewer-experts-98-7-coding-performance--860nh2pje","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"","timeRequired":"PT11M","video":{"@type":"VideoObject","name":"Qwen3.8-Flash-Next Shrunk to 58GB — 50% Fewer Experts, 98.7% Coding Performance!","description":"Qwen3.8-Flash-Next is a massive Mixture-of-Experts model, but this new GSQ-RCO Coder variant from ISTA-DASLab takes a very different approach to...","thumbnailUrl":"https://i.ytimg.com/vi/gtYdl3m5KMQ/sddefault.jpg","uploadDate":"2026-10-01T13:08:14.442Z","duration":"PT11M","url":"https://api.daily.dev/r/860NH2pje","embedUrl":"https://www.youtube.com/embed/gtYdl3m5KMQ"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Execute Automation","item":"https://daily.dev/sources/executeautomation"},{"@type":"ListItem","position":3,"name":"Qwen3.8-Flash-Next Shrunk to 58GB — 50% Fewer Experts, 98.7% Coding Performance!"}]} ```