Vedic-Native-SLM-1.1B

1.1B parameter SLM for ARM64 edge devices. Uses Vedic math kernels:

  • Nikhilam Sparsha: 3.15x softmax
  • Anurupya KV Cache: 341x memory reduction
  • Vilokanam: Script-aware sparse output

Intended Use: Offline agricultural AI, multilingual Q&A, sovereign computing.

Limitations: ARM64 only. No GPU. 4GB RAM minimum.

Author: Joydeep Das (divineearthly)

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support