Ling-3.0-flash

Ling-3.0-flash gives agent builders a large-capability MoE with only ~5.1B active parameters, so inference cost per token sits far below its capability class — and the week-long free window on Nous Portal lets you benchmark it on real coding and tool-use traces before committing to a provider.

• 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.
• 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.
• inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.

• postNous Research automates local model setup in Hermes Desktop
• postHermes Desktop picks and configures a local model from your hardware
• articleDownload Hermes Desktop to get started:
• postBots are coming to Hermes Desktop 🤖

• articleLing 3.0 flash VL fp4 releasedInclusionAI model releases
• postLing-3.0-flash: a 124B MoE with 5.1B active parameters for agentsAnt Ling
• postLing-3.1-flash: 1M-context MoE with long-horizon coding resultsAnt Ling

Checking sign-in…

Loading comments…