EdgeMind Stats Dashboard
Real-time performance metrics and system status
AI Models
4
Available
Model Size
~250MB
Total All Models
Inference Speed
15-30
tokens/second
Privacy Score
100%
Client-Side
Performance by Device
| Device | Expected Speed | Memory Usage | Rating |
|---|---|---|---|
| Desktop (Modern Chrome/Firefox) | 25-40 tok/s | 200-400 MB | Excellent |
| Desktop (Safari/Edge) | 10-25 tok/s | 200-350 MB | Good |
| Mobile (High-end: iPhone 14+, Pixel 7+) | 8-20 tok/s | 150-300 MB | Moderate |
| Mobile (Mid-range) | 3-10 tok/s | 100-200 MB | Limited |
Model Specifications
LLM
Falcon-H1-Tiny-90M
90M
parameters
- Size
- 91MB
- Repository
- onnx-community/Falcon-H1-Tiny-90M-Instruct-ONNX
Embeddings
all-MiniLM-L6-v2
22M
parameters
- Size
- 45MB
- Repository
- sentence-transformers/all-MiniLM-L6-v2