Ollama Cloud Adds MiniMax M3 for Frontier Agentic Coding and 1M Context

OllamaOllama

Ollama has made the MiniMax M3 model available on its Cloud, providing US-based access with zero data retention. This integration offers a frontier-level, open-weight model for agentic coding and multimodal tasks, featuring a 1-million-token context window. It expands access to advanced AI capabilities for complex, autonomous workflows.

Ollama's Cloud now hosts the MiniMax M3 model. It is the first open-weights model to combine frontier coding, agentic capabilities, a 1-million-token context, and native multimodality (processing text and images). It supports autonomous task decomposition, tool invocation, and multi-step reasoning.
Data Retention
Zero
Location
US-based
Access
ollama launch (tools), ollama run (chat)
Integrations
Claude Code, Codex

Hosting MiniMax M3 gives developers a frontier-grade foundation for AI coding assistants and automated workflows, a capability previously limited to closed-source models. Its proprietary Sparse Attention architecture enables efficient 1M-token processing, and it scored 83.5 on BrowseComp for autonomous browsing.

Run on Ollama's privacy-sensitive US infrastructure, the model plugs directly into agentic coding tools and chat workflows, giving teams a frontier open-weights option without managing their own hardware.

View the full update on ollama.com
ollama
ollama
@ollama
X

.@MiniMax_AI M3 model is available on Ollama's Cloud! In partnership with MiniMax, the M3 model on Ollama's Cloud is US-based with zero data retention. Try M3 on coding and agentic tasks: Claude Code: ollama launch claude --model minimax-m3:cloud Codex: ollama launch codex --model minimax-m3:cloud Chat: ollama run minimax-m3:cloud and more! 👇👇👇

48retweets534likes
View on X

Still wondering? A few quick answers below.

MiniMax M3 is an open-weights model that combines frontier coding and agentic capabilities, a 1-million-token context window, and native multimodality. It is designed for autonomous task decomposition, tool invocation, and multi-step reasoning.

You can access MiniMax M3 on Ollama's Cloud using ollama launch commands for specific agentic coding tools like Claude Code and Codex, or ollama run for general chat interactions.

Key features include top-tier performance on coding and agentic benchmarks, a 1-million-token context window powered by MiniMax Sparse Attention, and native multimodality for processing text and images. It also offers strong autonomous browsing capabilities.

The MiniMax M3 model on Ollama's Cloud is US-based and operates with a zero data retention policy. This means no user data is stored, addressing privacy concerns for commercial usage.

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

Share this update