• 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.
• tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
• reasoning model — A model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.
• 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.

A 7.9B hybrid reasoning model with 1.3B active parameters and native tool calling is available through OpenRouter and Vercel's gateway, so cheap small-model agent loops can be tested before committing to a larger model.

• postKeeping Transformed Weights Resident Cuts SGLang Cold Starts to Seconds
• postLing-3.0-tiny Measured on the Phone-Class Intelligence and Speed Frontier
• postLing-3.0-flash-Fin Takes Auditable Tool Chains Into Financial Work
• postLing-2.6-1T Lands on OpenRouter With a Fast-Thinking Cost Cut

• postLing-3.0-tiny ships open weights in BF16, FP8 and INT4Ant Ling
• postAnt Group has released Ling 3.0 Tiny, which scores 25 on the Artificial…Artificial Analysis
• postLing-3.0-flash: a 124B MoE with 5.1B active parameters for agentsAnt Ling

Checking sign-in…

Loading comments…