Ollama launch command release

Ollama has released the the ollama launch command in version 0.15+, which simplifies the deployment of coding tools by automating the setup and execution of integrations like Claude Code, OpenCode, and Codex. This update removes the need for manual environment variables or configuration files to get these tools running with either local or cloud-based models.

Automated Setup for Coding Tools

The ollama launch command provides a one-command setup process that guides users through model selection and integration launch. This eliminates the traditional requirement for manual configuration files or environment variables.

Supported Integrations

Ollama now officially supports the following coding tool integrations via the launch command:

  • Claude Code
  • OpenCode
  • Droid
  • Codex

Configuration-Only Mode

Users who wish to configure a tool without immediately executing it can use the --config flag:

ollama launch opencode --config

Model Recommendations and Context Length

To ensure optimal performance for coding tools, Ollama recommends updating the context length in the application settings to at least 64,000 tokens.

Local Model Options

For users running models locally, the following models are recommended:

  • glm-4.7-flash (Requires approximately 23 GB VRAM for 64,000 tokens context length)
  • qwen3-coder
  • gpt-oss:20b

Cloud Model Options

For users with limited local hardware, Ollama provides cloud-hosted models with full context length and generous free tier limits. Recommended cloud models include:

  • glm-4.7:cloud
  • minimax-m2.1:cloud
  • gpt-oss:120b-cloud
  • qwen3-coder:480b-cloud

Extended Coding Sessions and Cloud Services

Ollama has expanded its cloud service offerings to coincide with this release. The service provides hosted models with full context length and extended 5-hour coding session windows to support longer development workflows. Detailed pricing and limits can be found at ollama.com/pricing.

Sources

Related

  • Dispatch
    Ollama v0.14.0: Anthropic API Compatibility and Claude Code Support

    Ollama v0.14.0 introduces compatibility with the Anthropic Messages API, enabling the use of Claude Code and other Anthropic SDK applications with local and cloud open-source models.

  • Dispatch
    Ollama Coding Models and Integrations Update

    Ollama has introduced cloud access to GLM-4.6 and Qwen3-Coder-480B, alongside updates to Qwen3-Coder-30B and expanded integrations for VS Code, Zed, and Droid.

  • Dispatch
    Ollama Cloud Models Preview

    Ollama has introduced Cloud models in preview, enabling users to run large-scale models on datacenter-grade hardware while maintaining the same local toolset and API integration.

  • Project
    ollama/ollama

    Ollama is a cross‑platform runtime that lets you download and run open‑source large language models locally. It offers a CLI, a REST API (localhost:11434), and official Python/JS SDKs, plus many community integrations (web UIs, LangChain, AutoGPT, etc.). Install with a one‑line script or Docker, then launch models like `ollama run gemma4` or use `ollama launch` to connect to coding assistants or personal bots.

  • Dispatch
    Ollama adds Subagents and Web Search to Claude Code

    Ollama now supports subagents and web search within Claude Code, allowing models to run parallel tasks and access real-time information without requiring MCP servers or API keys.