deepseek-ai/DeepSeek-V2-Lite
Text Generation
•
16B
•
Updated
•
146k
•
155
Hebangwen
hebangwen
AI & ML interests
None yet
Recent Activity
reacted
to
yeonseok-zeticai's
post
with 🚀
2 days ago
⚡ MobileCLIP2 Complete On-device Study: TMLR 2025 Featured Model on Mobile
Major Release: Comprehensive mobile deployment study of Apple's MobileCLIP2 (TMLR August 2025 Featured) with detailed performance benchmarks across 52+ mobile devices!
🎯 Model Overview:
- Architecture: Multi-modal reinforced training (vision + language)
- Research: TMLR 2025 Featured Certification
- Innovation: Improved efficiency-accuracy trade-offs vs SigLIP/OpenAI CLIP
- Specialty: Zero-shot image classification and retrieval
📊 Mobile Performance Results:
Latency Metrics:
- NPU (Best): 9.74ms average inference
- GPU: 39.00ms average
- CPU: 494.89ms average
- NPU Advantage: 115.94x speedup over CPU baseline!
Memory Efficiency:
- Model Size: 1.66 GB (production optimized)
- Runtime Memory: 466.18 MB peak consumption
- Load Range: 0-1,884 MB across device categories
- Inference Range: 431-1,616 MB
Accuracy Preservation:
- FP16 Precision: 39.78 dB maintained
- Quantized Mode: 15.07 dB (INT optimization available)
- Zero-shot Quality: Production-grade vision-language matching
🏆 Research Highlights:
MobileCLIP2-S4 Performance:
- Matches SigLIP-SO400M/14 accuracy
- 2x fewer parameters
- 2.5x lower latency than DFN ViT-L/14
MobileCLIP-S0 Efficiency:
- Similar zero-shot performance to OpenAI ViT-B/16
- 4.8x faster inference
- 2.8x smaller model size
MobileCLIP-S2 Advantages:
- Better avg zero-shot than SigLIP ViT-B/16
- 2.3x faster, 2.1x smaller
- Trained with 3x less seen samples
MobileCLIP-B (LT) Accuracy:
- 77.2% ImageNet zero-shot
- Surpasses OpenAI ViT-L/14@336
- Better than DFN and SigLIP similar architectures
🔗 Resources:
- Complete Study: https://mlange.zetic.ai/p/Steve/MobileCLIP2-image
Ready to build vision-language applications that run entirely on-device?
The future of multi-modal AI runs locally in everyone's pocket! 🚀
liked
a model
6 days ago
deepseek-ai/DeepSeek-V2-Lite
liked
a model
11 days ago
meituan-longcat/LongCat-Video-Avatar
Organizations
liked
a
model
6 days ago
liked
a
model
11 days ago
liked
a
model
12 days ago
liked
a
model
20 days ago
liked
a
model
2 months ago
liked
5
models
3 months ago
mradermacher/Qwen3-30B-A3B-abliterated-erotic-GGUF
31B
•
Updated
•
587
•
8
deepseek-ai/DeepSeek-V3.1-Terminus
Text Generation
•
685B
•
Updated
•
23.4k
•
•
358
meituan-longcat/LongCat-Flash-Thinking
Text Generation
•
562B
•
Updated
•
38
•
146
openbmb/VoxCPM-0.5B
Text-to-Speech
•
Updated
•
1.71k
•
780
google/gemma-3n-E2B-it
Image-Text-to-Text
•
5B
•
Updated
•
210k
•
244
liked
a
Space
4 months ago
liked
a
model
6 months ago
liked
3
models
7 months ago
liked
a
model
8 months ago
liked
a
model
10 months ago
liked
a
dataset
10 months ago
liked
a
model
10 months ago
liked
a
model
11 months ago
