Alibaba Drops Qwen3.8 Flash Next
The model uses a new design with 125 billion parameters in total. Even with that high count, it only uses 6 billion parameters for each word it processes. This makes it very fast and much cheaper to train than previous versions.
Technically the system relies on new components like the Gated DeltaNet and an N-gram embedding table. These additions help the model handle complex tasks while keeping computing costs low. It is a major shift in how they build their architecture.
Keep in mind that running this model yourself requires a lot of power. The file size is over 170 gigabytes. You will need high-end hardware and plenty of memory to get it running on your own servers.
Comments (0)
No comments yet. Be the first!
More AI news
NewsNew AI Tool Fixes Mistakes in Financial Research
Researchers developed a new framework to stop AI from learning from its own bad data in financial trading models.
NewsPerplexity adds local AI to Mac apps
The new update lets your Mac handle some AI tasks directly on your computer.
NewsMeta Releases Muse Image Model on Fal
Meta has launched a new AI model on the Fal platform that plans and edits images on its own.