---
title: Celeste Imperia | Hardware-Aware AI Forge
emoji: 🌌
colorFrom: blue
colorTo: purple
sdk: static
pinned: true
thumbnail: >-
  https://cdn-uploads.huggingface.co/production/uploads/697f74cb005a67fc114da2b4/OCwnTMS-RIt9cPQR0Gnxf.png
license: apache-2.0
tags:
- edge-ai
- qnn
- quantization
- openvino
- windows-on-arm
---

# Celeste Imperia | Hardware-Aware AI Forge

**Bridging the gap between frontier AI architectures and consumer silicon.**

Celeste Imperia specializes in the precision optimization of LLMs, VLMs, and Diffusion architectures. We provide hardware-validated weights optimized for private, zero-latency execution across Qualcomm, Intel, and NVIDIA ecosystems.

---

## 🏗️ The Development Forge: Workstation V2.0
All models are forged on a specialized dual-GPU pipeline to ensure stability across both "Masses-Ready" and "Professional" hardware.

| Component | **Legacy Validation Rig** | **Current AI Workstation** |
| :--- | :--- | :--- |
| **Processor** | Intel Core i5-11400 | Intel Core i5-11400 (6C/12T) |
| **Primary GPU** | NVIDIA RTX A4000 (16GB) | **NVIDIA RTX 3090 (24GB GDDR6X)** |
| **Secondary GPU** | - | **NVIDIA RTX A4000 (16GB GDDR6)** |
| **Memory** | 16GB RAM | **64GB DDR4 RAM** |
| **Storage** | Standard SSD | **High-Speed NVMe, and HDD Storage Pool** |

---

## 📂 Active Repositories

### 🐉 Snapdragon & Mobile NPU (QNN Native)
* **[SDXL-QNN](https://huggingface.co/CelesteImperia/SDXL-QNN)** - Optimized for Qualcomm Hexagon NPU. Includes Python and C# automation tools.

### 🧠 Domain-Specific Reasoning
* **[Llama-3-Indian-Finance](https://huggingface.co/CelesteImperia/Llama-3-8B-Indian-Finance-Quant-v2.0-RELEASE)** - Specialized reasoning for Indian financial and regulatory sectors.

### 🎨 Cross-Platform Optimization (OpenVINO / GGUF)
* **[SDXL-OpenVINO-Trinity](https://huggingface.co/CelesteImperia/celeste-imperia-sdxl-openvino)** - 4-step generation for Intel i5/i7.
* **[Whisper-Large-V3-Turbo](https://huggingface.co/CelesteImperia/whisper-large-v3-turbo-openvino)** - High-speed speech-to-text.
* **[Qwen2-VL-2B-INT4](https://huggingface.co/CelesteImperia/Qwen2-VL-2B-Instruct-OpenVINO-INT4)** - Vision-language reasoning.
* **[Llama-3.2-1B-GGUF](https://huggingface.co/CelesteImperia/Llama-3.2-1B-Instruct-GGUF)** / **[Phi-3.5-GGUF](https://huggingface.co/CelesteImperia/Phi-3.5-mini-instruct-GGUF)** - Mobile-ready LLMs.

---

### ☕ Support the Forge
Maintaining a dual-GPU AI workstation and hosting high-bandwidth models requires significant resources. If our open-source tools power your projects, consider supporting our development:

| Platform | Support Link |
| :--- | :--- |
| **Global & India** | [Support via Razorpay](https://razorpay.me/@huggingface) |

**Scan to support via UPI (India Only):**

<img src="https://huggingface.co/datasets/CelesteImperia/Assets/resolve/main/QrCode.jpeg" width="200">

---

**Connect with the architect:** [Abhishek Jaiswal on LinkedIn](https://www.linkedin.com/in/abhishek-jaiswal-524056a/)