VQV Signal
According to a post on X by @koltregaskes2, Baidu has released ERNIE 5.5 Flash Preview, the first post-trained model built on its ERNIE 5.5 Flash Base. The model is listed with 280B total parameters, 14B active per token and a 1M-token context. It is available now through Baidu's Qianfan API, and Baidu says the model weights will follow.
According to a post on X by @koltregaskes2, Baidu has released ERNIE 5.5 Flash Preview, the first post-trained model built on its ERNIE 5.5 Flash Base. The model is listed with 280B total parameters, 14B active per token and a 1M-token context. It is available now through Baidu's Qianfan API, and Baidu says the model weights will follow.
AI-assisted summary based on the listed source.
Baidu has released ERNIE 5.5 Flash Preview, the first post-trained model on its ERNIE 5.5 Flash Base, with 280B total parameters, 14B active per token and a 1M-token context. It is available now through Baidu's Qianfan API, and Baidu says the weights will follow. Why it matters: Another large Chinese model headed...
The post frames this as another large Chinese model heading toward open weights, which it says adds pressure on US open-model builders. For developers, the weights are not yet released, so current access is through the Qianfan API. Watch whether Baidu publishes the weights and what terms come with them.
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.
