--- title: MiniMax M2 · Ollama Blog | daily.dev description: MiniMax M2, an open-source model built for coding and agentic workflows, is now available on Ollama's cloud via `ollama run minimax-m2:cloud`. The model has 10... canonical: https://daily.dev/posts/minimax-m2-ollama-blog-81zmr5bxz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: MiniMax M2 · Ollama Blog | daily.dev og:description: MiniMax M2, an open-source model built for coding and agentic workflows, is now available on Ollama's cloud via `ollama run minimax-m2:cloud`. The model has 10... og:url: https://daily.dev/posts/minimax-m2-ollama-blog-81zmr5bxz og:image: https://api.daily.dev/og/posts/81zMr5bXZ.png og:image:alt: MiniMax M2 · Ollama Blog 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. # MiniMax M2 · Ollama Blog **[Ollama](https://daily.dev/sources/ollama)** · 3 min read · 0 upvotes · 0 comments ## Summary MiniMax M2, an open-source model built for coding and agentic workflows, is now available on Ollama's cloud via `ollama run minimax-m2:cloud`. The model has 10 billion activated parameters (230 billion total) and reportedly ranks #1 among open-source models on Artificial Analysis's composite intelligence index, with strong Terminal-Bench and SWE-Bench performance. The post covers setup instructions for VS Code, Zed, Droid, and direct cloud API access. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I run MiniMax M2 using Ollama? Run the command 'ollama run minimax-m2:cloud' to access MiniMax M2 through Ollama's cloud service. The model can also be pulled with 'ollama pull minimax-m2:cloud' for use in tools like VS Code and Zed, or accessed directly via the ollama.com cloud API using an API key. _daily.dev tracks new model releases like MiniMax M2 for developers picking an agentic coding model._ ### How many parameters does MiniMax M2 have and why does that matter for coding agents? MiniMax M2 has 10 billion activated parameters out of 230 billion total, a sparse design intended to deliver lower latency, lower cost, and higher throughput for interactive agents and batched sampling, while still performing strongly on coding and agentic benchmarks like Terminal-Bench and SWE-Bench. _Developers comparing agentic coding models can follow releases like this on daily.dev._ ### How do I configure MiniMax M2 as a custom model in Droid? Add a custom_models entry to ~/.factory/config.json specifying model_display_name as MiniMax-M2, model as minimax-m2:cloud, base_url as http://localhost:11434/v1, api_key as not-needed, provider as generic-chat-completion-api, and max_tokens as 16384, then run Droid and use /model to switch to it. _daily.dev helps developers wiring new models into CLI agent tools like Droid stay current._ ## Similar posts on daily.dev - [MiniMax-M2: MoE Model for Agentic and Coding Capabilities](https://daily.dev/posts/minimax-m2-moe-model-for-agentic-and-coding-capabilities-hhvgfyxd8) · DigitalOcean Community · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#vscode](https://daily.dev/tags/vscode), [#ollama](https://daily.dev/tags/ollama) [View this post on daily.dev](https://daily.dev/posts/minimax-m2-ollama-blog-81zmr5bxz) ```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":"MiniMax M2 · Ollama Blog","url":"https://daily.dev/posts/minimax-m2-ollama-blog-81zmr5bxz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/minimax-m2-ollama-blog-81zmr5bxz"},"datePublished":"2026-08-23T12:23:53.155Z","dateModified":"2026-08-23T12:57:32.079Z","description":"MiniMax M2, an open-source model built for coding and agentic workflows, is now available on Ollama's cloud via `ollama run minimax-m2:cloud`. The model has 10...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/03fb1a10ef158f8986c9778334c2af42?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Ollama","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":"Ollama","logo":"https://media.daily.dev/image/upload/s--dRYYkBCj--/f_auto,q_auto/v1787487632/logos/ollama-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/ollama"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/minimax-m2-ollama-blog-81zmr5bxz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,vscode,ollama","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Ollama","item":"https://daily.dev/sources/ollama"},{"@type":"ListItem","position":3,"name":"MiniMax M2 · Ollama Blog"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/minimax-m2-ollama-blog-81zmr5bxz#faq","mainEntity":[{"@type":"Question","name":"How do I run MiniMax M2 using Ollama?","acceptedAnswer":{"@type":"Answer","text":"Run the command 'ollama run minimax-m2:cloud' to access MiniMax M2 through Ollama's cloud service. The model can also be pulled with 'ollama pull minimax-m2:cloud' for use in tools like VS Code and Zed, or accessed directly via the ollama.com cloud API using an API key. daily.dev tracks new model releases like MiniMax M2 for developers picking an agentic coding model."}},{"@type":"Question","name":"How many parameters does MiniMax M2 have and why does that matter for coding agents?","acceptedAnswer":{"@type":"Answer","text":"MiniMax M2 has 10 billion activated parameters out of 230 billion total, a sparse design intended to deliver lower latency, lower cost, and higher throughput for interactive agents and batched sampling, while still performing strongly on coding and agentic benchmarks like Terminal-Bench and SWE-Bench. Developers comparing agentic coding models can follow releases like this on daily.dev."}},{"@type":"Question","name":"How do I configure MiniMax M2 as a custom model in Droid?","acceptedAnswer":{"@type":"Answer","text":"Add a custom_models entry to ~/.factory/config.json specifying model_display_name as MiniMax-M2, model as minimax-m2:cloud, base_url as http://localhost:11434/v1, api_key as not-needed, provider as generic-chat-completion-api, and max_tokens as 16384, then run Droid and use /model to switch to it. daily.dev helps developers wiring new models into CLI agent tools like Droid stay current."}}]} ```