Latest SOTA models supported on Qualcomm NPU.
AI & ML interests
On Device AI Deployment and Research
Organization Card
Welcome to Nexa AI org on HuggingFace!
NexaâŻAI is an on device AI deployment and research company. We craft optimized foundation models and on-device inference framework that runs any model on any device, across any backendâwithin minutes. Our mission is to make on device AI frictionâfree and productionâready.
On this page youâll find
- Our own trained checkpoints
- Handâpicked community models in GGUF or MLX formats, ready to run on nexa-sdk
Resources
- âď¸ Download nexaSDK â get up and run models locally in minutes
- đŹ Discord Community
- đź Slack Community
spaces 5
Running
Agents
67
Nexa Omni Demo
đ§
Generate text from uploaded or recorded audio
Runtime error
Agents
79
Omnivlm Dpo Demo
đ
Ask questions about images and get detailed answers
Paused
Agents
30
Open LLM Leaderboard for domains
đ
Ranking for Open-sourced LLMs in different domains
Paused
Agents
39
Nexa AI GGUF Convertor
âĄ
Submit a model for quantization and receive an email notification
models 103
NexaAI/LFM2-24B-A2B-GGUF
Text Generation ⢠24B ⢠Updated ⢠248 ⢠7
NexaAI/table-transformer-detection-npu
Updated
NexaAI/paddleocr-npu-mobile
Image-to-Text ⢠Updated ⢠29 ⢠3
NexaAI/depth-anything-v2-npu-mobile
Updated
NexaAI/depth-anything-v2-npu
Updated ⢠1
NexaAI/yolo26x-npu-mobile
Updated
NexaAI/yolo26s-npu-mobile
Updated
NexaAI/yolo26m-npu-mobile
Updated
NexaAI/yolo26l-npu-mobile
Updated
NexaAI/yolo26n-npu-mobile
Updated
datasets 0
None public yet