--- title: I used three local coding models for a week of real... description: A week-long hands-on comparison of three local open-weight coding models — Qwen3-Coder 30B, Devstral Small 2, and GPT-OSS 20B — tested on code generation, bug... canonical: https://daily.dev/posts/i-used-three-local-coding-models-for-a-week-of-real-work-and-the-smallest-one-won-z1tpb6zzg twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I used three local coding models for a week of real work, and the smallest one won | daily.dev og:description: A week-long hands-on comparison of three local open-weight coding models — Qwen3-Coder 30B, Devstral Small 2, and GPT-OSS 20B — tested on code generation, bug... og:url: https://daily.dev/posts/i-used-three-local-coding-models-for-a-week-of-real-work-and-the-smallest-one-won-z1tpb6zzg og:image: https://api.daily.dev/og/posts/z1tPb6zzg.png og:image:alt: I used three local coding models for a week of real work, and the smallest one won 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 used three local coding models for a week of real work, and the smallest one won **[XDA Developers](https://daily.dev/sources/xda-developers)** · 5 min read · 1 upvotes · 0 comments ## Summary A week-long hands-on comparison of three local open-weight coding models — Qwen3-Coder 30B, Devstral Small 2, and GPT-OSS 20B — tested on code generation, bug diagnosis, and refactoring using a Pygame Snake game. GPT-OSS 20B, the smallest model at 13GB, outperformed both larger competitors across every test: it generated the most robust code with unprompted safety features, correctly identified and fixed all three planted bugs with precise root-cause analysis, and produced a refactored script that ran identically to the original. Qwen3-Coder was fast but unreliable in refactoring, while Devstral Small 2 consistently shipped broken fixes. GPT-OSS earned the permanent spot in the author's local AI stack. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Experiences with local models for coding](https://daily.dev/posts/experiences-with-local-models-for-coding-jggvqgz1l) · Martin Fowler · 4 upvotes · 0 comments --- Tags: [#python](https://daily.dev/tags/python), [#llm](https://daily.dev/tags/llm), [#local-ai](https://daily.dev/tags/local-ai), [#ollama](https://daily.dev/tags/ollama) [View this post on daily.dev](https://daily.dev/posts/i-used-three-local-coding-models-for-a-week-of-real-work-and-the-smallest-one-won-z1tpb6zzg) ```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 used three local coding models for a week of real work, and the smallest one won","url":"https://daily.dev/posts/i-used-three-local-coding-models-for-a-week-of-real-work-and-the-smallest-one-won-z1tpb6zzg","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-used-three-local-coding-models-for-a-week-of-real-work-and-the-smallest-one-won-z1tpb6zzg"},"datePublished":"2026-07-25T22:04:28.282Z","dateModified":"2026-07-25T22:08:59.593Z","description":"A week-long hands-on comparison of three local open-weight coding models — Qwen3-Coder 30B, Devstral Small 2, and GPT-OSS 20B — tested on code generation, bug...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a7ca43796adbe34f80cf61fe936ea9ed?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a7ca43796adbe34f80cf61fe936ea9ed?_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-used-three-local-coding-models-for-a-week-of-real-work-and-the-smallest-one-won-z1tpb6zzg","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,llm,local-ai,ollama","timeRequired":"PT5M"} {"@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 used three local coding models for a week of real work, and the smallest one won"}]} ```