DeepSeek-V4.1-Flash Begins Rolling Out on Ollama Cloud
Key Info
DeepSeek-V4.1-Flash is being rolled out on Ollama's cloud platform, initially available to Max and Team subscribers, with Ollama saying it is quickly adding capacity to reach all subscribers.
Highlights
- DeepSeek-V4.1-Flash is described as the smallest model in a new DeepSeek architecture family, featuring native visual understanding.
- It is positioned as smarter, faster, and more efficient, with improved inference speed, higher throughput, and a path to scaling to larger models.
- The rollout is staged: Max and Team accounts get access first, followed by all subscribers as capacity grows.