Change8

v0.6.2

📦 ollamaView on GitHub →
3 features🐛 2 fixes🔧 4 symbols

Summary

This release introduces multi-image support and memory optimizations for Gemma 3, adds support for AMD Strix Halo GPUs, and fixes issues with model quantization and saving.

✨ New Features

  • Support for multiple images in Gemma 3
  • Added support for AMD Strix Halo GPUs
  • Enabled 'ollama create --quantize' when converting Gemma 3 from safetensors

🐛 Bug Fixes

  • Fixed high system memory consumption when running Gemma 3
  • Fixed issue where the '/save' command failed for models containing a '/' in their name

🔧 Affected Symbols

Gemma 3ollama create --quantize/saveAMD Strix Halo