teolm30/fox1.2

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Mar 29, 2026Architecture:Transformer Featherless Exclusive Cold

teolm30/fox1.2 is a compact, fine-tuned Qwen2.5-0.5B model with approximately 494 million parameters and a 32,768-token context length. Developed by teolm30 (OpenClaw Community), it is specifically optimized for 100% OpenClaw agent tool execution, excelling at smart tool selection and generation for various agent workflows. This model is designed for efficient local inference on consumer hardware, making it ideal for integrating comprehensive tool-use capabilities into agentic applications.

Loading preview...

Fox1.2 OpenClaw: Agent Tool Execution Model

Fox1.2 OpenClaw is a highly efficient, fine-tuned Qwen2.5-0.5B model developed by teolm30, specifically engineered for seamless integration with the OpenClaw agent framework. With approximately 494 million parameters and a substantial 32,768-token context window, this model is optimized for local inference and runs effectively on consumer hardware with as little as 6GB VRAM.

Key Capabilities

  • Comprehensive OpenClaw Tool Support: Fully supports all OpenClaw agent tools, including exec (shell commands), read/write/edit (file operations), web_search/web_fetch (web operations), process (background session management), memory_search/memory_get, and cron job management.
  • Smart Tool Selection: Excels at intelligently determining when and how to use specific tools based on user prompts, generating tool calls in a structured JSON format.
  • Compact & Fast: Its small size (~994MB F16) and optimized architecture ensure rapid execution, making it suitable for resource-constrained environments.
  • Agent Workflow Optimization: Trained on over 200 examples covering diverse OpenClaw tool patterns, ensuring robust performance in generating and executing tool calls within agentic workflows.

Good For

  • Developers building OpenClaw-powered agents requiring extensive tool-use capabilities.
  • Applications needing a compact and fast model for local inference that can interact with system resources, web services, and manage processes.
  • Scenarios where intelligent tool orchestration is critical for automating complex tasks.