Instructions to use Arjun9350/ai24x7-vision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Arjun9350/ai24x7-vision with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Arjun9350/ai24x7-vision:Q5_K_M # Run inference directly in the terminal: llama cli -hf Arjun9350/ai24x7-vision:Q5_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Arjun9350/ai24x7-vision:Q5_K_M # Run inference directly in the terminal: llama cli -hf Arjun9350/ai24x7-vision:Q5_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Arjun9350/ai24x7-vision:Q5_K_M # Run inference directly in the terminal: ./llama-cli -hf Arjun9350/ai24x7-vision:Q5_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Arjun9350/ai24x7-vision:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Arjun9350/ai24x7-vision:Q5_K_M
Use Docker
docker model run hf.co/Arjun9350/ai24x7-vision:Q5_K_M
- LM Studio
- Jan
- Ollama
How to use Arjun9350/ai24x7-vision with Ollama:
ollama run hf.co/Arjun9350/ai24x7-vision:Q5_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Arjun9350/ai24x7-vision with Docker Model Runner:
docker model run hf.co/Arjun9350/ai24x7-vision:Q5_K_M
- Lemonade
How to use Arjun9350/ai24x7-vision with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Arjun9350/ai24x7-vision:Q5_K_M
Run and chat with the model
lemonade run user.ai24x7-vision-Q5_K_M
List all available models
lemonade list
- Atomic Chat
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
AI24x7 Vision SaaS
Product - CCTV AI Analysis
Model: Qwen3VL-8B Fine-tuned v10 (CCTV domain, 28 images, 3 epochs)
Format: GGUF Q5_K_M (5.5GB, CPU inference)
Hardware: 32GB RAM, AMD Ryzen 7 5800X, NO GPU needed
Price Machine: ₹42-50K
One Command Install
curl -sL https://huggingface.co/Arjun9350/ai24x7-vision/resolve/main/install.sh | bash
Architecture
Customer CCTV Camera → AI24x7 Agent (₹42K machine) → Cloud GPU API → Telegram Alerts
Cloud GPU Server
- API: http://43.242.224.231:5050/analyze
- Model: Qwen3VL-8B v10 (CCTV fine-tuned)
- Format: GGUF Q5_K_M (5.5GB)
Pricing
- Starter: ₹999/month (4 cameras)
- Business: ₹2,999/month (10 cameras)
- Enterprise: ₹9,999/month (unlimited + WhatsApp API)
API Endpoints
| Method | Endpoint | Description |
|---|---|---|
| GET | /health | Health check |
| POST | /analyze | Analyze CCTV image |
Support
- Telegram Bot: @ai24x7_vision_bot
- Developer: Arjun Singh
Files
- model-q5_k_m.gguf (5.5GB) - AI Model
- install.sh - One command installer
- Downloads last month
- 8
Hardware compatibility
Log In to add your hardware
5-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support