January 2026 Summaries

Ollama launch is a command that simplifies setting up and running coding tools like Claude Code, OpenCode, and Codex by using local or cloud models without the need for environment variables or config files. Users can get started by downloading Ollama v0.15+ and running specific commands in a terminal, with a requirement of around 23 GB VRAM for local models and a context length of 64,000 tokens. The tool supports integrations with models such as glm-4.7-flash and gpt-oss:20b for local use, and glm-4.7:cloud and qwen3-coder:480b-cloud for cloud use. It caters to extended coding sessions by allowing for a 5-hour window and offers a cloud service that provides full context length and generous usage limits, even at the free tier. Additionally, users can configure tools without launching them immediately, providing flexibility and convenience in managing coding workflows.

Ollama has introduced image generation capabilities on macOS, with plans to expand to Windows and Linux. Users can generate images by running "ollama run x/z-image-turbo" along with a prompt, and the images save to their current directory, with terminals like Ghostty and iTerm2 supporting inline previews. The Z-Image Turbo model, developed by Alibaba's Tongyi Lab, features 6 billion parameters and excels in creating photorealistic images with bilingual text rendering in English and Chinese. It is available under Apache 2.0 for commercial use. Another model, FLUX.2 Klein from Black Forest Labs, is optimized for text rendering in images, available in 4B and 9B parameter sizes, with the former open for commercial use under Apache 2.0. Users can customize image generation by adjusting parameters such as image size, number of steps, random seed, and negative prompts. Future developments include extending support to Windows and Linux, adding new image generation models, and incorporating image editing capabilities.

Ollama v0.14.0 and later versions now support the Anthropic Messages API, enabling users to utilize Claude Code, Anthropic's agentic coding tool, with both local and cloud-based open-source models. This integration allows the execution of Claude Code on local machines or through Ollama's cloud services, with recommendations to use models with at least 64k tokens context length for optimal performance. Users can install Claude Code on various operating systems and configure environment variables to connect to Ollama, using models such as gpt-oss:20b and glm-4.7:cloud for coding purposes. Furthermore, existing applications leveraging the Anthropic SDK can be adapted to interface with Ollama by adjusting the base URL, and the platform supports tool calling, multi-turn conversations, and other advanced features. For comprehensive setup and configuration details, users are encouraged to consult the Claude Code guide.

OpenAI's Codex CLI can be utilized with open models through Ollama, allowing users to read, modify, and execute code within their working directory using models like gpt-oss:20b or gpt-oss:120b. To start, users should install the Codex CLI via npm and initiate it with the --oss flag, which defaults to using the local gpt-oss:20b model. Codex requires a substantial context window, with a recommendation of at least 32K tokens, and users can adjust the context length as needed. Model switching is facilitated by using the -m flag, and all models on Ollama Cloud are compatible with Codex. Additional setup instructions and configuration options can be found in the Codex integration guide.