DeepSeek-V4-Flash-0731成Ollama增长最快模型
DeepSeek-V4-Flash-0731在Ollama上跑得超快，100tps+，还零数据留存，一条命令就能上手，试试呗。
Ollama宣布DeepSeek-V4-Flash-0731成为其有史以来token使用量增长最快的模型。Ollama正在美国和欧洲扩展该模型的服务器容量。
该模型在Ollama上运行速度超过100tps，并且零数据保留。用户的数据完全归自己所有，可通过ollama run deepseek-v4-flash:0731-cloud命令直接使用。
DeepSeek-V4-Flash-0731 is Ollama's fastest growing model ever in token usage. We are scaling capacity in US & Europe. On Ollama, this model runs with high performance (100tps+) and zero data retention. Your data stays yours. ollama run deepseek-v4-flash:0731-cloud📊 64 ⚡
This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include DeepSeek-V4-Flash-0731, Ollama, DeepSeek, 数据隐私.
Source attribution: curated from ollama (@ollama).
