New coding models & integrations

2025-10-15 · Source: Ollama Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

Ollama announced the availability of new coding models, GLM-4.6 and Qwen3-coder-480B, on its cloud service as of October 16, 2025. Qwen3-Coder-30B has also been updated for enhanced tool calling capabilities within Ollama's new engine. Users can run these models via simple `ollama run` commands, with Qwen3-coder:480b also available for local deployment for systems with over 300GB of VRAM. The announcement includes detailed instructions for integrating these models with popular coding environments like VS Code, Zed, and Droid. Additionally, Ollama provides direct cloud API access for models like `glm-4.6` and `qwen3-coder:480b`, requiring an API key for authentication.

Key takeaway

For Machine Learning Engineers and Software Engineers seeking to integrate advanced coding LLMs into their development workflow, Ollama's new GLM-4.6 and Qwen3-coder models offer flexible cloud and local deployment options. You should explore the direct integrations with VS Code, Zed, and Droid to streamline code generation and tool calling, potentially accelerating your project development cycles.

Key insights

Ollama expands its coding model offerings and integrations for enhanced developer workflows.

Principles

• Cloud and local model access
• Streamlined IDE integration

Method

Access coding models via `ollama run` commands or integrate them into IDEs like VS Code, Zed, and Droid by pulling models and configuring provider settings.

In practice

• Generate single-page apps with detailed prompts
• Use `ollama pull` for local IDE access
• Configure `~/.factory/config.json` for Droid

Topics

• Coding LLMs
• Ollama Cloud
• Developer Tool Integration
• GLM-4.6
• Qwen3-Coder

Best for: Machine Learning Engineer, Software Engineer, Prompt Engineer

Related on AIssential

• 100% Free Claude Code | Run Claude Code with Local LLM with Ollama and Qwen 3.5 — Local LLMs can be integrated with Quad Code via Ollama for specific coding tasks, offering a viable alternative to API-based solutions.
• Tool support — Ollama now enables LLMs to interact with external tools for complex tasks via a new API feature.
• GLM 5.2: NEW Opensource KING IS BEATING GPT-5.5 & Opus 4.8! (Fully Tested) — GLM 5.2 is a new open-source model matching or exceeding proprietary LLMs in specific creative and coding tasks at a fraction of the cost.
• not much happened today — Open models are rapidly advancing in coding and privacy, while enterprise AI platforms are consolidating agentic capabilities and specialized hardware.
• ollama launch — Ollama introduced the `ollama launch` command on January 23, 2026, simplifying the setup and execution of popular coding tools like Claude Code, OpenCode, and Codex with both local and cloud-based AI…
• Run Qwen3.5 on an Old Laptop: A Lightweight Local Agentic AI Setup Guide — Local AI setups are accessible on older hardware using lightweight models and tools like Ollama and OpenCode.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Ollama Blog.