New Ollama Features: Instant Model Switching, Subagents, and Built‑in Web Search

The latest Ollama 0.16.1 release lets users switch models and tools instantly, use Claude Code, Codex, and OpenClaw without extra configuration, and enables Subagents and built‑in web search directly via simple commands.

Old Zhang's AI Learning
Old Zhang's AI Learning
Old Zhang's AI Learning
New Ollama Features: Instant Model Switching, Subagents, and Built‑in Web Search

Ollama now offers a one‑click launch for the newly open‑sourced Qwen3.5 model: ollama run qwen3.5:cloud Earlier releases already provided free cloud models such as Kimi‑K2.5, GLM‑5, and MiniMax‑M2.5, which could be configured to agents like Claude Code, Opencode, and OpenClaw.

After upgrading to version 0.16.1, the ollama command itself can switch instantly between models and different tools, meaning Claude Code, Codex, OpenClaw and similar agents can be used without any additional setup.

The update also adds support for Claude Code Subagents and built‑in web search, eliminating the need for an MCP server or API key. The feature is enabled with a single command, for example:

ollama launch claude --model minimax - m2.5:cloud

Subagents can run parallel tasks such as file search or code exploration; some models automatically trigger Subagents when needed, while users can also invoke them manually.

Web search is integrated into the Anthropic‑compatible layer, allowing models to fetch up‑to‑date information directly, and Subagents can also leverage this search capability for concurrent research.

The author notes that seamless model switching has been Ollama’s “killer feature,” and the current updates broaden that advantage by unifying models, interfaces, and development experiences.

Large Language ModelOllamaweb searchClaude CodeModel Switchingsubagents
Old Zhang's AI Learning
Written by

Old Zhang's AI Learning

AI practitioner specializing in large-model evaluation and on-premise deployment, agents, AI programming, Vibe Coding, general AI, and broader tech trends, with daily original technical articles.

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.