Srevarshan1502/NutriMinds-3B-Merged

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 13, 2026Architecture:Transformer Featherless Exclusive Cold

NutriMinds-3B-Merged by Srevarshan1502 is a 3.1 billion parameter clinical AI engine, fine-tuned from Qwen2.5-3B-Instruct with a 32768 token context length. It specializes in analyzing food items and ingredient labels against 52 medical conditions, providing evaluations in a strict JSON schema. This model is designed for integration into automated healthcare applications and recipe generation pipelines, acting as an expert clinical nutritionist.

Loading preview...

NutriMinds-3B-Merged: Clinical Nutrition AI Engine

NutriMinds-3B-Merged is a specialized 3.1 billion parameter clinical AI engine developed by Shrisudarsanah at SRM University. Built upon the Qwen/Qwen2.5-3B-Instruct base model and fine-tuned using Supervised Fine-Tuning (SFT) with 16-bit Merged LoRA Weights, this model excels at nutritional analysis.

Key Capabilities

  • Specialized Clinical Analysis: Evaluates food items and ingredient labels against 52 distinct medical conditions, including Type 2 Diabetes, Celiac Disease, and Chronic Kidney Disease.
  • Structured JSON Output: Designed to output evaluations in a strict, predictable JSON schema, facilitating seamless integration into automated systems.
  • Expert Clinical Nutritionist: Acts as an expert clinical nutritionist and medical analyst, providing compatibility scores, risk alerts, and clinical rationale.
  • High Context Length: Features a 32768 token context length, allowing for comprehensive input analysis.

Intended Use Cases

  • Automated Healthcare Applications: Ideal as a backend inference engine for applications requiring automated dietary recommendations or food suitability assessments.
  • Recipe Generation Pipelines: Can be integrated into systems that generate recipes tailored to specific medical conditions.
  • Medical Profile Analysis: Accepts a patient's medical profile and a food label/item to return detailed suitability evaluations.

Important Note

This model is an academic tool for analytical demonstration and should not replace professional medical diagnosis or treatment. It requires a specific ChatML template and system prompt to trigger its JSON generation behavior.