HimalayaGPT 0.5B

HimalayaGPT 0.5B is a 500-million-parameter instruction-tuned model built by Himalaya AI Research Lab and trained on a Nepali-language corpus with a custom Nepali BPE tokenizer. The project’s stated mission is digital sovereignty for AI-native governance in Nepal — deployed in production behind civic services like the Nagarik App and Hello Sarkar.

ScaLabs Cloud hosts HimalayaGPT 0.5B on our Kathmandu hardware for free. No deposit, no monthly minimum, no tier requirement. If you’re building something Nepali — civic tech, a Nepali-language chatbot, a translation pipeline, an offline-replacement experiment — point your OpenAI SDK at our endpoint and you’re in.

Why we host it for free

We’re a Nepali-first cloud. Hosting the country’s sovereign LLM as a public good is the easy decision. Compute is cheap on local hydropower; the work that went into HimalayaGPT belongs to the community that built it.

Fair-use limits still apply (we will rate-limit obvious abuse — spam, resale, runaway loops) but real Nepali-language workloads will not hit them.

When to pick it

• Anything Nepali-language: civic tech, government workflows, content for Nepali audiences, Nepali chat agents
• Multilingual agents where one path is Nepali and the others go through Qwen / Gemma / Minimax
• Edge / offline replacement experiments where a 0.5B model on local hardware is the right tool
• Educational and research use — first-class welcome here

When to look elsewhere

• Any non-Nepali workload — use Qwen 3.6 27B or Gemma 4 26B A4B instead
• Long-context reasoning over 8K tokens — pick a larger MoE
• General coding agents — the catalog’s dense and MoE LLMs are the better fit

Credit

The model and weights are by the Himalaya AI Research Lab team. We are the host, not the author. The Hugging Face page and the lab’s GitHub have the model cards, tokenizer, and training pipeline.