Biography

Hi, my name is Darshani Ranjith Persadh, I qualified as a software engineer in 2005, applying technology to improve transportation efficiency and sustainability. Today, I specialize in quantum computing for agriculture and efficient inference for large-scale language models. My work bridges production-ready model deployment and academic research, while preserving programming capabilities.

I am actively involved in the open-source community, contributing to Github and Hugging Face ecosystems. My recent work on quantized DeepSeek-V4 variants has gathered significant attention, with nearly 1.35K downloads within the first 24 hours, reflecting the growing need for practical MoE inference solutions.

Selected publications & models

2026

persadian/DeepSeek-V4-Flash-GGUF

A Quantized 284B Mixture-of-Experts Language Model by Darshani Persadh
Hugging Face Repository · DOI: 10.57967/hf/8828
▼ 1.35K downloads (first 24h) 799 in 8h → +186
📄 View full documentation →
2026

persadian/DeepSeek-V4-Flash-IQ1_S-XL

Merged single-file quantized MoE by Darshani Persadh
Hugging Face · DOI: 10.57967/hf/8853
Single-file GGUF (57.3GB) · 284B parameters · 1M context
📘 View Merged edition docs → 📄 View DFQS_v1.0_IEEE_Specification →
2025

Quantum for Agriculture

Optimizing Crop Yields on Q29, South Coast, Durban by Persadh, D.R. & Persadh, J.
DOI 10.5281/14867426
2023

Quantum focused Neuroscience

Persadh, D.R.
Stanford University, School of Medicine

Research: impact & adoption

~The DeepSeek-V4-Flash-GGUF model gained rapid traction within the open-source community: 799 downloads in the first 8 hours after release, surpassing 1.35K downloads within 24 hours. This reflects strong demand for efficient, deployable MoE models that balance size (284B parameters) with practical hardware requirements (80GB+ RAM, RTX 3090 class). The model's two-shard GGUF format and custom V4-aware fork enable researchers to experiment with state-of-the-art MoE architectures on commodity hardware.


~The Neuroscience and the Connection to Exemplary Leadership Preview with Professor Baba Shiv alongside a few of my peers from my cohort (Mrityunjaya (Jay) Tomar, Linn Eide, Prabhakar Rawat, Bryce Au, Bruno CHAPPUIS, Maneesh Deshpande, Bob Michael Lama, Iris (Xu) Yan) had us discussing how to distinguish the work of our emotional brain from the work of our rational brain.

Talks

PM Modi Meets Indian-Origin Tech Leaders in South Africa G20 Tech & Innovation Leaders Summit (November 2025)

Forbes Sustainability Summit Forbes On 5th (October 2025)

Cartier Womens Initiative Science & Technology AMA Session (September 2025)

Africa Tech Festival EQL:HER - Womenomics Africa (November 2023)

Articles

Hackernoon Bits to Qubits: Decoding my dive into the IBM Quantum Challenge 2024

Hackernoon Deepfakes — A Looming Threat or Misplaced Fear?

IBM Sustainability Leveraging IBM Maximo's IoT Capabilities To Drive Digital Transformation in Agriculture

IBM AI and Data Science Generative AI: How to Navigate the Gray Area

IBM AI and Data Science The Metaverse and Sustainability: An Ongoing Evolution

Pearson The price of virtual art: non-fungible tokens demystified

Pearson Around the World series: We live in a society that loves to consume radical change


Last updated: May 2026 · Built with ❤️ by @persadian for Research & Code-centric workflows. Copyright © 2010. All Rights Reserved.