NVIDIA DGX Spark
Ollama announced on October 13, 2025 that it has partnered with NVIDIA around the NVIDIA DGX Spark, stating that Ollama runs fast and efficiently out-of-the-box on the device.
The DGX Spark is powered by the NVIDIA GB10 Grace Blackwell Superchip and delivers 1 petaFLOP of performance for prototyping and running local language models on Ollama, according to the announcement. The device has 128GB of memory.
Ollama said that with that memory, users can run the latest models from Alibaba (Qwen), DeepSeek, Meta (Llama), Mistral, Google (Gemma), OpenAI (Gpt-oss), and many more from Ollama's library. Users can also upload and bring their own custom or fine-tuned models.
Ollama added that it is working with NVIDIA to optimize Ollama's performance and is testing it across the use cases it sees most often: chat, document processing (retrieval, OCR, modification), code tasks, and multimodal workflows.
The announcement did not include pricing, availability or benchmark results for Ollama on the DGX Spark.
Based on reporting from the original publisher. Visit the source for full context and later updates.
Publisher excerpt
The latest NVIDIA DGX Spark is here! Ollama has partnered with NVIDIA to ensure it runs fast and efficiently out-of-the-box.