JeongMinMin/Qwen3-1.7B-base-MED

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 2, 2026Architecture:Transformer Featherless Exclusive Cold

JeongMinMin/Qwen3-1.7B-base-MED is a 2 billion parameter language model based on the Qwen3 architecture. This model is a base version, indicating it is a foundational model without specific instruction tuning. With a context length of 32768 tokens, it is designed for general language understanding and generation tasks. Its primary utility lies in serving as a robust base for further fine-tuning on specialized downstream applications.

Loading preview...

Model Overview

JeongMinMin/Qwen3-1.7B-base-MED is a foundational language model with approximately 2 billion parameters, built upon the Qwen3 architecture. This model is presented as a base version, meaning it has not undergone instruction-tuning and is intended as a general-purpose language model. It supports a substantial context window of 32768 tokens, allowing it to process and generate longer sequences of text.

Key Characteristics

  • Model Family: Qwen3 architecture.
  • Parameter Count: Approximately 2 billion parameters.
  • Context Length: Supports up to 32768 tokens, suitable for tasks requiring extensive context.
  • Base Model: This is a pre-trained base model, not instruction-tuned, making it versatile for various downstream adaptations.

Potential Use Cases

Given its nature as a base model, JeongMinMin/Qwen3-1.7B-base-MED is well-suited for:

  • Further Fine-tuning: Ideal as a starting point for domain-specific fine-tuning or task-specific adaptations.
  • Feature Extraction: Can be used to extract rich contextual embeddings for various NLP tasks.
  • Research and Development: Provides a solid foundation for exploring language model capabilities and architectural modifications.