What's Changed (this repo branch)

• Sync to v0.13.5
• Advise to disable flash attention on older AMD APUs in the README

What's Changed (from Ollama)

New Models

• Nemotron 3 Nano: A new Standard for Efficient, Open, and Intelligent Agentic Models
• Olmo 3 and Olmo 3.1: A series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets.
• Google's FunctionGemma a specialized version of Google's Gemma 3 270M model fine-tuned explicitly for function calling.

What's Changed

• Enable Flash Attention automatically for models by default
• Fixed handling of long contexts with Gemma 3 models
• Fixed issue that would occur with Gemma 3 QAT models or other models imported with the Gemma 3 architecture
• bert architecture models now run on Ollama's engine
• Added built-in renderer & tool parsing capabilities for DeepSeek-V3.1
• Fixed issue where nested properties in tools may not have been rendered properly

New Contributors

• @familom made their first contribution in ollama#13220
• @nathannewyen made their first contribution in ollama#13469

Full Changelog: v0.13.3...v0.13.5