ERNIE 5.5 Flash-Base
Baidu's large new model for developers and researchers, free to download; it is a starting point for building their own AI tools and needs powerful servers to run.
trckr found this on Nov 9, 4 days after it came out, so it sent no alert. Its release date comes from Hugging Face.
Key facts
- Released
- Nov 5, 2026
- What it does
- Text and chat: Writes, answers questions and holds a conversation.
Can I use it?
In an app
No app mentioned so far.
For developers
No developer access mentioned so far.
Download
Free to download and run on your own computer: it has Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open"..
How it scores
Not in the independent rankings yet. New models usually show up within a few weeks, and this page updates when they do.
Compare ERNIE 5.5 Flash-Base with
It came out 599 days after ERNIE-4.5-VL-424B-A47B (文心大模型4.5), the lab's previous model.
The details
A 290 billion parameters: Data-centre scale: it runs on many chips (GPUs) at once. Parameters are the numbers a model learns: a rough measure of its size. Mixture of experts (MoE): A design that splits a big model into many "expert" parts and uses only a few for each word. It gives big-model quality at closer to small-model speed. text model from Baidu, with about 14B parameters active per Tokens: The small chunks of text a model reads and writes, about three-quarters of a word each. Prices and limits are counted in tokens., trained from scratch on 33.5T tokens with a 128K training context and up to A 1M-token context window: It can keep about 750,000 words, or 2,500 book pages in mind at once: the question, any files you share, and its own replies. for Fine-tune: Extra training that adapts an existing model to a narrower job, like answering medical questions or writing in a company's style. and Inference: Running a trained model to get an answer. Training builds the model once; inference happens every time someone uses it.. Released as the end-of-pre-training base Checkpoint: A saved copy of a model at one point in its training. Labs share checkpoints for researchers; they're rarely finished products. under the ERNIE 5.5 Flash base model license, free to download.
Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.
baidu/ERNIE-5.5-Flash-Basebaidu/ERNIE-5.5-Flash-Base-BF16Timeline
/GitHub ggml-org/llama.cppFirst signal
Get alerts like this the moment they happen.
From Baidu and every other major lab.