--- title: Viability of local models for coding | daily.dev description: A Thoughtworks technologist shares hands-on experience running local LLMs for agentic coding over four weeks on Apple Silicon hardware (M3 Max 48GB and M5 Pro... canonical: https://daily.dev/posts/viability-of-local-models-for-coding-1cgbfrvir twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Viability of local models for coding | daily.dev og:description: A Thoughtworks technologist shares hands-on experience running local LLMs for agentic coding over four weeks on Apple Silicon hardware (M3 Max 48GB and M5 Pro... og:url: https://daily.dev/posts/viability-of-local-models-for-coding-1cgbfrvir og:image: https://api.daily.dev/og/posts/1CGbFRViR.png og:image:alt: Viability of local models for coding 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. # Viability of local models for coding **[Martin Fowler](https://daily.dev/sources/mafo)** · 12 min read · 0 upvotes · 0 comments ## Summary A Thoughtworks technologist shares hands-on experience running local LLMs for agentic coding over four weeks on Apple Silicon hardware (M3 Max 48GB and M5 Pro 64GB). The post systematically covers the key factors affecting viability: RAM constraints, processing power, memory bandwidth, parameter count, reasoning capabilities, tool calling reliability, model format (GGUF vs MLX), quantization levels, MoE vs dense architecture, context window size, runtime choice (LM Studio), and harness compatibility (OpenCode, Pi, Claude Code). Key findings include: Qwen3.6 35B MoE offers the best balance of capability and RAM footprint; reasoning mode can actually hurt performance for smaller models; tool calling remains unreliable but models often self-correct; and the overall experience is still too messy for plug-and-play developer use. A follow-up memo covering specific task results is promised. ## 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 - [Running local models on an M4 with 24GB memory](https://daily.dev/posts/running-local-models-on-an-m4-with-24gb-memory-iezpeho6j) · Hacker News · 4 upvotes · 0 comments - [Local LLM Hardware Requirements: Mac vs PC 2026](https://daily.dev/posts/local-llm-hardware-requirements-mac-vs-pc-2026-57ttll1fg) · SitePoint · 2 upvotes · 0 comments - [My 8GB GPU shouldn't run flagship local LLMs, but this workflow makes it work anyway](https://daily.dev/posts/my-8gb-gpu-shouldn-t-run-flagship-local-llms-but-this-workflow-makes-it-work-anyway-nb2r0gq97) · XDA Developers · 1 upvotes · 0 comments --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding), [#local-ai](https://daily.dev/tags/local-ai), [#qwen](https://daily.dev/tags/qwen), [#lm-studio](https://daily.dev/tags/lm-studio) [View this post on daily.dev](https://daily.dev/posts/viability-of-local-models-for-coding-1cgbfrvir) ```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":"Viability of local models for coding","url":"https://daily.dev/posts/viability-of-local-models-for-coding-1cgbfrvir","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/viability-of-local-models-for-coding-1cgbfrvir"},"datePublished":"2026-07-07T12:43:36.474Z","dateModified":"2026-07-07T12:44:04.173Z","description":"A Thoughtworks technologist shares hands-on experience running local LLMs for agentic coding over four weeks on Apple Silicon hardware (M3 Max 48GB and M5 Pro...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fdba2315927b3b3d7066d9703c986bf2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fdba2315927b3b3d7066d9703c986bf2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Martin Fowler","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":"Martin Fowler","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/mafo","url":"https://daily.dev/sources/mafo"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/viability-of-local-models-for-coding-1cgbfrvir","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-coding,local-ai,qwen,lm-studio","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Martin Fowler","item":"https://daily.dev/sources/mafo"},{"@type":"ListItem","position":3,"name":"Viability of local models for coding"}]} ```