Model Releases
We are now enabling a queue for DeepSeek v4 Pro, expect longer time-to-first-token instead of degrading service. please bear with us 🙏🙏🙏…
Ollama has implemented a queue system for DeepSeek v4 Pro to manage high demand, which will result in longer initial response times rather than service degradation. Users are requested to be patient d
Ollama has implemented a queue system for DeepSeek v4 Pro to manage high demand, which will result in longer initial response times rather than service degradation. Users are requested to be patient during this period as the system processes requests in order.
Source: Ollama (X) | 2026-04-27