awesome-llms-on-device
github.com/nexaai/awesome-llms-on-device ↗Awesome LLMs on Device: A Comprehensive Survey
1.2k
GitHub Stars
52
Curated Resources
7
Categories
1 month ago
Last Refreshed
🚀 Why This Hub is a Must-ReadFoundations and PreliminariesEfficient Architectures for On-Device LLMsModel Compression and Optimization Techniques for On-Device LLMsHardware Acceleration and Deployment StrategiesApplicationsTutorials and Learning Resources
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me popular on-device llms framework resources from awesome-llms-on-device"
Installation instructions →What's inside
Efficient Architectures for On-Device LLMs
- Any-Precision LLM
Supports multiple precisions efficiently
- Breakthrough Memory
Up to 4.5× performance improvement
- JetMoE
Outperforms Llama27B and 13B-Chat with fewer parameters
- Pangu-$$ Pro
Neural architecture, parameter initialization, and optimization strategy for billion-level parameter models
- [Paper]Mixture-of-Experts (MoE) Architectures
- [Paper]Mixture-of-Experts (MoE) Architectures
Applications
- BioMistral-7B
- DriveVLM
- Gboard smart reply
- LLMCadCollaborative and Hierarchical Model Approaches
- Octopus v3
🚀 Why This Hub is a Must-Read
Hardware Acceleration and Deployment Strategies
Tutorials and Learning Resources
Foundations and Preliminaries
- [Octopus]Evolution of On-Device LLMs
- [Paper]The Performance Indicator of On-Device LLMs
- [Paper]The Performance Indicator of On-Device LLMs
- [Paper]Limitations of Cloud-Based LLM Inference and Advantages of On-Device Inference
- [Paper]Limitations of Cloud-Based LLM Inference and Advantages of On-Device Inference
- [Paper]On-Device LLMs Training
Showing a sample of 52 resources. View the full list on GitHub →