DeepSeek-V4-Flash Becomes Fastest Growing Model on Ollama with Zero Data Retention

ollama · x · 2026-08-05

Ollama officially announced that DeepSeek-V4-Flash-0731 is the fastest growing model ever in token usage on its platform. The model runs with high performance (100tps+) and guarantees zero data retention.

Users can run it via ollama run deepseek-v4-flash:0731-cloud. Ollama is currently scaling up its compute capacity in the US and Europe.

Related event: DeepSeek-V4-Flash Tops Ollama Growth Chart(2 posts)→

Original post →

More from Models

Models channel →