software-zetic/YOLO26n
Updated
ZeticAI
software-zetic
AI & ML interests
None yet
Recent Activity
published
a model
8 days ago
software-zetic/YOLO26n
updated
a model
13 days ago
ZETIC-ai/mediapipe-hand-detection
updated
a model
13 days ago
ZETIC-ai/mediapipe-pose-estimation
Organizations
published
a
model
8 days ago
updated
8
models
13 days ago
ZETIC-ai/mediapipe-hand-detection
Object Detection
ā¢
Updated
ZETIC-ai/mediapipe-pose-estimation
Object Detection
ā¢
Updated
ZETIC-ai/chronos-bolt-tiny
Time Series Forecasting
ā¢
Updated
ZETIC-ai/whisper-tiny-encoder
Automatic Speech Recognition
ā¢
Updated
ZETIC-ai/whisper-tiny-decoder
Automatic Speech Recognition
ā¢
Updated
ZETIC-ai/whisper-small-decoder
Automatic Speech Recognition
ā¢
Updated
ZETIC-ai/YOLO26l
Object Detection
ā¢
Updated
ZETIC-ai/YOLO26s
Object Detection
ā¢
Updated
all-mpnet-base-v2 Complete On-device Study: SOTA Sentence Embeddings on Mobile
#42 opened 4 months ago
by
software-zetic
reacted to
yeonseok-zeticai's
post with šš
5 months ago
Post
3719
ā” RexBERT Complete On-device Study: Comprehensive Performance Analysis Across Mobile Devices
(Check details at https://mlange.zetic.ai/p/Steve/RexBERT)
TL;DR: Transformer models are now practical for real-time mobile applications. The cloud-to-edge AI migration is complete.
- Original model from @thebajajra
šÆ Study Overview:
- Model: RexBERT (ModernBERT for E-commerce)
- Focus: Real-world deployment viability and performance analysis
š Key Performance Metrics:
Latency Results:
- NPU (Best): 4.74ms average
- GPU: 12.56ms average
- CPU: 35.16ms average
NPU Advantage: 16.98x speedup over CPU
Memory Efficiency:
- Model Size: 568.96 MB (compressed for mobile)
- Runtime Memory: 299.01 MB peak consumption
- Load Memory Range: 285 MB - 1,072 MB across devices
Accuracy Preservation:
- FP16 Precision: 63.72 dB
- Quantized Mode: Available with minimal accuracy loss
- Inference Quality: Production-grade maintained
š Technical Implementation:
(Runnable with Copy & Paste at the ZETIC.MLange link: https://mlange.zetic.ai/p/Steve/RexBERT)
This study demonstrates that:
Transformer models are viable for real-time mobile applications
NPU acceleration provides the breakthrough needed for practical deployment
Mobile-first AI architecture is now technically feasible
The performance gap between cloud and edge inference is rapidly closing
š Real-World Applications Enabled:
E-commerce Intelligence:
- Instant product search and discovery
- Real-time semantic matching
- Context-aware recommendations
- Natural language query processing
Conversational Commerce:
- Voice-to-product search
- Chatbot-style shopping assistance
- Intent recognition and classification
- Multi-turn conversation handling
Privacy-First AI:
- On-device processing (no data transmission)
- GDPR/privacy regulation compliant
- Reduced server infrastructure costs
- Offline capability maintenance
Are you ready to integrate BERT-level language understanding into your mobile applications?
(Check details at https://mlange.zetic.ai/p/Steve/RexBERT)
TL;DR: Transformer models are now practical for real-time mobile applications. The cloud-to-edge AI migration is complete.
- Original model from @thebajajra
šÆ Study Overview:
- Model: RexBERT (ModernBERT for E-commerce)
- Focus: Real-world deployment viability and performance analysis
š Key Performance Metrics:
Latency Results:
- NPU (Best): 4.74ms average
- GPU: 12.56ms average
- CPU: 35.16ms average
NPU Advantage: 16.98x speedup over CPU
Memory Efficiency:
- Model Size: 568.96 MB (compressed for mobile)
- Runtime Memory: 299.01 MB peak consumption
- Load Memory Range: 285 MB - 1,072 MB across devices
Accuracy Preservation:
- FP16 Precision: 63.72 dB
- Quantized Mode: Available with minimal accuracy loss
- Inference Quality: Production-grade maintained
š Technical Implementation:
(Runnable with Copy & Paste at the ZETIC.MLange link: https://mlange.zetic.ai/p/Steve/RexBERT)
This study demonstrates that:
Transformer models are viable for real-time mobile applications
NPU acceleration provides the breakthrough needed for practical deployment
Mobile-first AI architecture is now technically feasible
The performance gap between cloud and edge inference is rapidly closing
š Real-World Applications Enabled:
E-commerce Intelligence:
- Instant product search and discovery
- Real-time semantic matching
- Context-aware recommendations
- Natural language query processing
Conversational Commerce:
- Voice-to-product search
- Chatbot-style shopping assistance
- Intent recognition and classification
- Multi-turn conversation handling
Privacy-First AI:
- On-device processing (no data transmission)
- GDPR/privacy regulation compliant
- Reduced server infrastructure costs
- Offline capability maintenance
Are you ready to integrate BERT-level language understanding into your mobile applications?