fableforge-ai/NEXUS-Medical

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 5, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

NEXUS-Medical by fableforge-ai is a 1.5 billion parameter instruction-tuned language model, based on Qwen2.5-1.5B-Instruct, specialized for medical Q&A and clinical reasoning. This lightweight model achieves a 93% score across domain knowledge, uncensored medical and general queries, reasoning, and tool use, demonstrating strong performance for its size. It is designed as a domain specialist within the FableForge NEXUS family, offering uncensored responses in healthcare contexts.

Loading preview...

NEXUS-Medical: A Specialized Medical LLM

NEXUS-Medical, developed by fableforge-ai, is a 1.5 billion parameter instruction-tuned language model built upon the Qwen2.5-1.5B-Instruct architecture. It is specifically designed as a domain specialist for medical question-answering and clinical reasoning, forming part of the FableForge NEXUS family of lightweight, expert models.

Key Capabilities & Performance

Despite its compact size, NEXUS-Medical demonstrates robust performance, achieving a 93% overall score in a 30-prompt evaluation. This evaluation, conducted on an NVIDIA A40 via Ollama, assessed various critical areas:

  • Domain Knowledge: Scored 4.7/5 (47/50)
  • Uncensored (Domain & General): Achieved 4.4/5 and 4.8/5 respectively, highlighting its ability to provide direct, uncensored responses in medical and general contexts.
  • Reasoning: Scored a perfect 5.0/5 (25/25), indicating strong analytical capabilities.
  • Tool Use: Scored 4.4/5 (22/25).

This benchmark performance positions NEXUS-Medical as a highly capable model for its parameter count, excelling in specialized medical applications.

Part of the NEXUS Family

NEXUS-Medical is one of six specialized models in the NEXUS family, each focusing on a distinct domain while maintaining a small footprint. Other family members include NEXUS-Coder, NEXUS-Security, NEXUS-Legal, NEXUS-Finance, and NEXUS-Science, collectively offering a suite of expert LLMs.

Use Cases

This model is particularly well-suited for applications requiring accurate and uncensored medical information, clinical reasoning, and general Q&A within a healthcare context. Its lightweight nature makes it efficient for deployment in environments with limited resources.

Finetunes
1 models