# inclusionAI releases Ling-3.0-flash-Sante, a 124B healthcare model

Digest AI · Generative AI & Models · published 2026-10-22T15:18:35Z

Canonical: https://digestai.news/story/inclusionai-releases-ling-3-0-flash-sante-a-124b-healthcare-model

## Summary

inclusionAI announced Ling-3.0-flash-Sante, a research‑grade language model built on the Ling-3.0-flash foundation and aimed at medical reasoning, healthcare research, and tool‑assisted workflows. The model contains 124 billion total parameters but activates only 5.1 billion per token thanks to a hybrid‑linear MoE architecture that combines Kimi Delta Attention, gated MLA, and sparse MoE layers. It supports a 256 K token context window, enabling long‑document analysis and evidence synthesis.

The team evaluated Sante on a suite of professional healthcare benchmarks, including AFUMED‑Drug, AFUSAFE‑MedSCE, MedMCQA, BrowseComp, HLE, DeepSearchQA, and Tau3‑Banking, reporting strong results across medical knowledge, safety, and complex reasoning tasks. The model is released on Hugging Face and ModelScope, but the announcement stresses that it is a research model, not a medical device; outputs may be incomplete or incorrect and must be reviewed by qualified professionals before any high‑stakes use. Deployment instructions are provided for Docker, SGLang, and vLLM, and the model recorded five downloads in the past month.

## Key points

- Ling-3.0-flash-Sante has 124 B parameters, activates 5.1 B per token, and supports a 256 K token context window.
- Targeted at medical reasoning and research, but labeled a research model that requires professional review and is not a medical device.
- Benchmarked on healthcare tasks such as AFUMED‑Drug, AFUSAFE‑MedSCE, MedMCQA, BrowseComp, HLE, DeepSearchQA, and Tau3‑Banking with strong performance.

## Why it matters

A large, long‑context model specialized for healthcare could speed evidence synthesis and AI‑assisted medical workflows, while its research‑only status highlights safety and regulatory challenges.

## Sources

1. [inclusionAI/Ling-3.0-flash-Sante · Hugging Face](https://huggingface.co/inclusionAI/Ling-3.0-flash-Sante) (huggingface.co, 2026-10-22, primary source)

Part of the developing story: [InclusionAI's Multilingual AI Model Journey](https://digestai.news/thread/inclusionai-releases-ming-3-0-audio-flash-a-multilingual-audio-language-model) (2 stories)

## Cite

Digest AI, "inclusionAI releases Ling-3.0-flash-Sante, a 124B healthcare model", 22 October 2026, https://digestai.news/story/inclusionai-releases-ling-3-0-flash-sante-a-124b-healthcare-model

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/inclusionai-releases-ling-3-0-flash-sante-a-124b-healthcare-model.json