Ollama

NVIDIA Jetson

<img src="https://github.com/user-attachments/assets/c8a43d1f-f6a0-4471-80b7-708307035e38" width="320" />

Ollama now supports NVIDIA Jetson. To install Ollama on NVIDIA Jetson devices, run:

curl -fsSL https://ollama.com/install.sh | sh

New models

<img src="https://github.com/user-attachments/assets/86bd9015-ecfd-48bb-bdad-5589b12dea20" width="360" />

• Qwen 2.5 Coder: Qwen 2.5 Coder series of models are now updated in 6 sizes: 0.5B, 1.5B, 3B, 7B, 14B and 32B.
• OpenCoder: an open and reproducible code LLM family which includes 1.5B and 8B models, supporting chat in English and Chinese languages.
• Athene V2: a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.

What's Changed

• Reliability improvements when hitting context limits
• Fixed extraneous newlines when displaying template/system layers when running ollama show
• Fixed issue where llama3.2-vision would crash when bring run on multiple NVIDIA GPUs
• Fixed error when embeddings contains only whitespace
• ollama create will now report line numbers for Modelfile errors

New Contributors

• @arbusam made their first contribution in https://github.com/ollama/ollama/pull/7580
• @neomantra made their first contribution in https://github.com/ollama/ollama/pull/7604
• @frances720 made their first contribution in https://github.com/ollama/ollama/pull/7517
• @ivostoykov made their first contribution in https://github.com/ollama/ollama/pull/5827
• @prasad89 made their first contribution in https://github.com/ollama/ollama/pull/7521
• @joey5403 made their first contribution in https://github.com/ollama/ollama/pull/7418

Full Changelog: https://github.com/ollama/ollama/compare/v0.4.1...v0.4.2