ainewsblitz.com

Breaking

Ant Group's inclusionAI Releases Ling-3.0-flash, a 124B MoE Model With Just 5.1B Active Parameters for Agent Workloads

Ant Group's inclusionAI Releases Ling-3.0-flash, a 124B MoE Model With Just 5.1B Active Parameters for Agent Workloads
  • Foundation Models
  • AI Agents

Ant Group's AGI unit, inclusionAI, has released Ling-3.0-flash, a hybrid-reasoning Mixture-of-Experts model with 124 billion total parameters but only 5.1 billion activated per token, aimed squarely at production-scale AI agents. The model went live on July 23, 2026, with immediate availability through the company's open API and third-party platforms, and a documentation page detailing its specifications.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year