Intel / article

Ling-3.0-flash

Source: portal.nousresearch.com
Author: NousResearch
Date: Published Jul 23, 2026

Context

Ling-3.0-flash's size figures describe two different things: the parameters in the whole model and those used for each text token. InclusionAI's model card reports 124 billion total parameters and 5.1 billion active per token.

Its architecture selects eight of 512 routed expert components for each token. That selective computation explains how it can draw on a large pool of learned parameters while activating a smaller portion at each step. The active count describes its computational design; it is not a measured response speed.

Terms in this piece · Glossary

mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.

Read the source portal.nousresearch.com