--- title: I stopped using Qwen and Gemma after finding a local LLM... description: A personal account of adding DeepSeek R1 Distill to a local LLM stack alongside Qwen and Gemma. The author explains what makes R1 Distill different — it's a... canonical: https://daily.dev/posts/i-stopped-using-qwen-and-gemma-after-finding-a-local-llm-that-actually-thinks-before-answering-rw52ognjv twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I stopped using Qwen and Gemma after finding a local LLM that actually thinks before answering | daily.dev og:description: A personal account of adding DeepSeek R1 Distill to a local LLM stack alongside Qwen and Gemma. The author explains what makes R1 Distill different — it's a... og:url: https://daily.dev/posts/i-stopped-using-qwen-and-gemma-after-finding-a-local-llm-that-actually-thinks-before-answering-rw52ognjv og:image: https://api.daily.dev/og/posts/rw52ogNJV.png og:image:alt: I stopped using Qwen and Gemma after finding a local LLM that actually thinks before answering 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. # I stopped using Qwen and Gemma after finding a local LLM that actually thinks before answering **[XDA Developers](https://daily.dev/sources/xda-developers)** · 4 min read · 0 upvotes · 0 comments ## Summary A personal account of adding DeepSeek R1 Distill to a local LLM stack alongside Qwen and Gemma. The author explains what makes R1 Distill different — it's a distilled version of DeepSeek's reasoning model, retrained on ~800K examples of R1's chain-of-thought across existing open models like Llama and Qwen variants. After testing it on reasoning-heavy tasks like UX heuristic evaluations, the author found it more reliable than generalist models for tasks requiring structured thinking. The takeaway is that no single consumer-grade model handles everything well, so matching specialized models to specific tasks is the smarter approach. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [I ran Gemma 4 and Qwen 3.5 for the same local tasks, and one pulled miles ahead](https://daily.dev/posts/i-ran-gemma-4-and-qwen-3-5-for-the-same-local-tasks-and-one-pulled-miles-ahead-ukuc7wocd) · XDA Developers · 0 upvotes · 0 comments - [DeepSeek R1 Complete Developer Guide \(2026\)](https://daily.dev/posts/deepseek-r1-complete-developer-guide-2026--4fd4kmmdh) · SitePoint · 0 upvotes · 0 comments - [I built Andrej Karpathy's "LLM Council" on my own hardware, and now no single model gets the last word](https://daily.dev/posts/i-built-andrej-karpathy-s-llm-council-on-my-own-hardware-and-now-no-single-model-gets-the-last-wo-hnojonqvd) · XDA Developers · 1 upvotes · 0 comments - [Beyond Benchmarks: Testing Open-Source LLMs in Multi-Agent Workflows](https://daily.dev/posts/beyond-benchmarks-testing-open-source-llms-in-multi-agent-workflows-u0si545tn) · Scott Logic · 2 upvotes · 0 comments - [A Gentle Introduction to Model Distillation](https://daily.dev/posts/a-gentle-introduction-to-model-distillation-mzqzy6iaj) · Machine Learning Mastery · 49 upvotes · 2 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#local-ai](https://daily.dev/tags/local-ai), [#ollama](https://daily.dev/tags/ollama), [#qwen](https://daily.dev/tags/qwen) [View this post on daily.dev](https://daily.dev/posts/i-stopped-using-qwen-and-gemma-after-finding-a-local-llm-that-actually-thinks-before-answering-rw52ognjv) ```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":"I stopped using Qwen and Gemma after finding a local LLM that actually thinks before answering","url":"https://daily.dev/posts/i-stopped-using-qwen-and-gemma-after-finding-a-local-llm-that-actually-thinks-before-answering-rw52ognjv","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-stopped-using-qwen-and-gemma-after-finding-a-local-llm-that-actually-thinks-before-answering-rw52ognjv"},"datePublished":"2026-07-24T17:03:05.577Z","dateModified":"2026-10-15T02:16:19.810Z","description":"A personal account of adding DeepSeek R1 Distill to a local LLM stack alongside Qwen and Gemma. The author explains what makes R1 Distill different — it's a...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/09dc2d3eed98cdb4d81bc07e584e5b2e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/09dc2d3eed98cdb4d81bc07e584e5b2e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"XDA Developers","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":"XDA Developers","logo":"https://media.daily.dev/image/upload/s--kCg6yyAP--/f_auto,q_auto/v1774964407/logos/xda-developers?_a=BAMAMiWQ0","url":"https://daily.dev/sources/xda-developers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/i-stopped-using-qwen-and-gemma-after-finding-a-local-llm-that-actually-thinks-before-answering-rw52ognjv","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,local-ai,ollama,qwen","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"XDA Developers","item":"https://daily.dev/sources/xda-developers"},{"@type":"ListItem","position":3,"name":"I stopped using Qwen and Gemma after finding a local LLM that actually thinks before answering"}]} ```