Baidu Releases ERNIE 5.5 Flash Base Open-Source Foundation Model with 280 Billion Parameters

Baidu has released ERNIE 5.5 Flash Base, an open foundation model with a mixture-of-experts architecture totaling 280 billion parameters, 14 billion active per input. It was pre-trained on 33.5 trillion tokens with up to 128,000-token training context and supports up to one million tokens during fine-tuning and inference. Weights are available on Hugging Face in FP8 and BF16. The base model ships without fine-tuning or post-training, with a post-trained version expected later. Baidu says it competes with similarly sized open foundation models such as DeepSeek V4 Flash and MiMo V2.5 in reasoning, code, and long-context tasks.