●Change8

v0.15.5-rc2

📦 ollamaView on GitHub →
✨ 5 features

Summary

This release introduces two new models, GLM-OCR and Qwen3-Coder-Next, and enhances core functionality with sub-agent support and VRAM-aware context length defaulting.

Migration Steps

  1. The 'ollama signin' command now opens a browser window for authentication.

✨ New Features

  • Added support for GLM-OCR, a multimodal OCR model.
  • Added Qwen3-Coder-Next, a coding-focused language model.
  • Introduced sub-agent support for 'ollama launch' for planning and research tasks.
  • Enabled GLM-4.7-Flash support on the experimental MLX engine.
  • Ollama now defaults context lengths based on available VRAM: 4k (< 24 GiB), 32k (24-48 GiB), and 262k (>= 48 GiB).