Primary sourceollama
View sourceEvent ·Multi-source
DeepSeek-V4-Flash-0731 成为 Ollama 云默认模型,输出速度 200+ tps
Ollama 宣布 DeepSeek-V4-Flash-0731 已全量上线其云平台,并成为 deepseek-v4-flash 的新默认模型。该模型在 Ollama 云上提供 200+ tps 输出速度,官方标注的持续输出速度为 120+ tps。托管采用零数据保留(ZDR)策略,服务区域覆盖美国和欧洲。Ollama 的 Pro 和 Max 套餐支持长时间多会话运行,适合搭配常用编码工具使用。
Current read
Ollama 云把 DeepSeek-V4-Flash 设为默认了,现在跑 200+ tps 还零数据保留,Pro 套餐能开多个长会话,写代码的可以试试。
9 sources58° AI heatLast updated 2026/8/8 06:24:31
Evidence
9 sourcesRelated source 1Geek
View sourceRelated source 2IT之家
View sourceRelated source 3arXiv: DeepSeek
View sourceRelated source 4AI Will
View sourceRelated source 5Pandaily
View sourceRelated source 6Decoder
View sourceRelated source 7歸藏(guizang.ai)
View sourceRelated source 8掘金本周最热
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.