Vikasit AI Writer 0.8B is a next-generation, sovereign Indian language model developed by Chandorkar Technologies. It is built on the Qwen 3.5 Hybrid Gated DeltaNet architecture, specifically optimized to provide high-density intelligence in a compact, on-device footprint.
As part of the Vikasit AI mission, this model is designed to provide India with a high-performance, locally-executable AI stack that respects data sovereignty and cultural context.
🚀 Model Highlights
Architecture: Hybrid Gated DeltaNet (O(1) memory for linear attention).
Parameters: 0.8 Billion.
Context Window: 256,144 tokens (Native).
Quantization: Custom iMatrix IQ4_XS (GGUF).
Size: ~504 MB.
Identity: Native Vikasit AI persona, refined for Indian professional and cultural nuances.
🛠 Quick Start (Ollama)
You can run this model locally with a single command:
