Kerassy/Qwen3.5-4B-Medical-Reasoning

VISIONConcurrent Unit Cost:1Model Size:4.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 25, 2026Architecture:Transformer Featherless Exclusive Cold

Kerassy/Qwen3.5-4B-Medical-Reasoning is a 4.5 billion parameter language model, fine-tuned for medical reasoning tasks. This model was converted to GGUF format using Unsloth, enabling efficient deployment. Its specialization in medical reasoning distinguishes it from general-purpose LLMs, making it suitable for applications requiring domain-specific understanding.

Loading preview...

Kerassy/Qwen3.5-4B-Medical-Reasoning Overview

This model is a 4.5 billion parameter variant of Qwen3.5, specifically fine-tuned for medical reasoning applications. It has been converted to the GGUF format, which is optimized for efficient inference on various hardware.

Key Characteristics

  • Medical Reasoning Focus: The model's fine-tuning is geared towards understanding and processing medical-related queries and information.
  • GGUF Format: Provided in GGUF format, facilitating compatibility with tools like llama-cli for both text-only and multimodal (with BF16-mmproj.gguf) usage.
  • Efficient Training: The fine-tuning process utilized Unsloth, which claims to offer 2x faster training speeds.

Available Model Files

Several quantized versions are available, including Q8_0.gguf, Q4_K_M.gguf, and BF16-mmproj.gguf for multimodal capabilities.

Good For

  • Applications requiring specialized medical knowledge and reasoning.
  • Developers looking for an efficiently trained and deployed medical LLM in GGUF format.
  • Use cases where a smaller, domain-specific model is preferred over larger, general-purpose alternatives.