By No Code MBA · Facts checked
- Provider
- InclusionAI
- Announcement date
- Status at last check
- Generally available
- Model family
- Ling-3.0
- Preceding model
- Ling-3.0-flash
- Capabilities
- Text
What changed
Ling-3.0-flash-Sante is a healthcare-specialized version of InclusionAI's Ling-3.0-flash. It is a hybrid-linear mixture-of-experts model with 124B total parameters and 5.1B active per token, combining Kimi Delta Attention, gated MLA and sparse MoE layers, with training extended to a 256K token context. InclusionAI reports evaluations on medical knowledge and safety, deep research and tool-assisted agent tasks, including MedMCQA, BrowseComp and Tau3-Banking, though numeric scores are published only as an image.
Access and availability
Open weights on Hugging Face at inclusionAI/Ling-3.0-flash-Sante under the MIT license. The model card includes a serving example with a 262,144-token context window.
Official access documentationWhat you can build
Use it only in a research sandbox to summarize medical literature with cited source passages, and have a qualified reviewer verify every claim before any consequential use.
Limitations
InclusionAI states it is a research model, not a medical device, and must not independently diagnose, prescribe or make treatment decisions. It may produce hallucinated or outdated medical information, and high-stakes use requires qualified professional review.