professorsynapse/nexus-tools_sft17-kto2

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Nov 28, 2025Architecture:Transformer Featherless Exclusive Cold

The professorsynapse/nexus-tools_sft17-kto2 is a 7 billion parameter language model developed by professorsynapse, featuring a 4096-token context length. This model is specifically fine-tuned for tool-use capabilities, making it suitable for applications requiring interaction with external functions or APIs. It is provided in both merged 16-bit and various GGUF quantized formats for flexible deployment across different hardware configurations.

Loading preview...

Model Overview

The professorsynapse/nexus-tools_sft17-kto2 is a 7 billion parameter language model developed by professorsynapse. This model has undergone a specific fine-tuning process, indicated by sft17-kto2, suggesting an optimization for tool-use scenarios. It is designed to facilitate interactions with external tools or functions, making it a strong candidate for applications that require dynamic action execution or API integration.

Key Features

  • Parameter Count: 7 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports a context window of 4096 tokens, allowing for processing moderately long inputs and maintaining conversational coherence.
  • Tool-Use Optimization: Specifically fine-tuned for tool-use, indicating enhanced capabilities in understanding and generating responses that involve external function calls.
  • Format Availability: Provided in multiple formats for broad compatibility:
    • Merged 16-bit: Full quality model for high-performance environments.
    • GGUF Quantizations: Includes various quantization levels (e.g., Q4_K_M, Q5_K_M, Q8_0) suitable for llama.cpp and Ollama, enabling deployment on consumer-grade hardware.

Ideal Use Cases

  • Function Calling: Applications that need to interpret user requests and translate them into calls to predefined functions or APIs.
  • Agentic Workflows: Developing AI agents capable of interacting with external systems to perform tasks.
  • Automated Task Execution: Scenarios where the model needs to orchestrate actions by utilizing a suite of tools.
  • Resource-Constrained Deployment: The availability of GGUF quantizations makes it suitable for deployment on devices with limited computational resources.

Finetunes
1 models