Key Info

Thinking Machines' Inkling 2 Small, a 594B mixture-of-experts model with a 1M context window, is now available on Ollama Cloud with zero data retention, runnable via ollama run inkling-2-small:cloud.

Highlights

  • 594B mixture-of-experts architecture with a 1M-token context window
  • Positioned for visual interpretation and creation, agentic knowledge work, and finance/quantitative reasoning
  • Listed use cases include OCR, grounding, infographic interpretation, visual reasoning, tool calling with MCP, and finance spreadsheet/filings reasoning
  • Available on Ollama Cloud with zero data retention; a dedicated model page is provided