Modelpublic

Arjun9350/ai24x7-cctv-qwen3-vl-8b-gguf

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face

0likes34downloads

Model Card

AI24x7 CCTV - Qwen3-VL-8B GGUF Model

Overview

This is a GGUF (Q5KM) quantized version of Qwen3-VL-8B, fine-tuned for Indian factory CCTV monitoring with Hindi language support.

Model Details

—Base Model: Qwen/Qwen3-VL-8B
—Quantization: Q5KM (5-bit)
—File Size: 5.5 GB
—Use Case: Hindi CCTV factory safety monitoring

Capabilities

—Fire detection in Hindi
—PPE (helmet, vest, gloves) violation detection
—Hindi CCTV incident reports
—Shift summary reports
—Safety compliance analysis

Usage

bash

# Download model
huggingface-cli download Arjun9350/ai24x7-cctv-qwen3-vl-8b-gguf model-q5_k_m.gguf

# Use with llama.cpp
./llama-server -m model-q5_k_m.gguf -c 4096 --host 0.0.0.0 --port 8080

Deployment

Deployed on AI24x7.cloud factory monitoring system at: 43.242.224.231:8080

Contact

Owner: Arjun Singh | AI24x7.cloud