HYU-NLP-EVAL/qwen3-4b-rar-medicine-static-r0-matched-dense-seed11-step-006

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:4BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Oct 1, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The HYU-NLP-EVAL/qwen3-4b-rar-medicine-static-r0-matched-dense-seed11-step-006 is a 4 billion parameter Qwen3 model, specifically a RaR-Medicine static R0 matched dense checkpoint. This model is designed for research use, focusing on medical applications. It is provided in BF16 format for inference and includes original veRL checkpoint files containing only model parameters. Its primary use case is research in the medical domain.

Loading preview...

Overview

This model, HYU-NLP-EVAL/qwen3-4b-rar-medicine-static-r0-matched-dense-seed11-step-006, is a 4 billion parameter Qwen3 variant. It represents a RaR-Medicine static R0 matched dense checkpoint, specifically from the run phase1-static-r0-medicine-qwen3-4b-matched-dense-20260928-seed11. The model is provided in BF16 format, optimized for inference tasks.

Key Capabilities

  • Medical Domain Focus: This checkpoint is specifically tuned for applications within the medical field, indicating specialized knowledge and performance in this area.
  • Research-Oriented: It is explicitly designated for research use, suggesting it may be suitable for experimental setups, academic studies, and development of new medical AI applications.
  • BF16 Inference: The model is available in BF16 (BFloat16) format, which is beneficial for efficient inference on compatible hardware, balancing performance and memory usage.

Good for

  • Medical Research: Ideal for researchers exploring language models in healthcare, drug discovery, clinical text analysis, or medical question answering.
  • Experimental Development: Suitable for developers and scientists prototyping new AI solutions in the medical domain.
  • Performance Evaluation: Can be used to evaluate the effectiveness of RaR-Medicine approaches on Qwen3 architecture for specific medical tasks.