Latest SOTA models supported on Qualcomm NPU.
AI & ML interests
On Device AI Deployment and Research
Recent Activity
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
Nexa AI infra to support Qwen3VL running on GPU/NPU/CPU
-
NexaAI/Qwen3-VL-4B-Instruct-GGUF
Image-Text-to-Text ⢠4B ⢠Updated ⢠25.4k ⢠25 -
NexaAI/Qwen3-VL-4B-Thinking-GGUF
Image-Text-to-Text ⢠4B ⢠Updated ⢠7.57k ⢠6 -
NexaAI/Qwen3-VL-8B-Instruct-GGUF
Image-Text-to-Text ⢠8B ⢠Updated ⢠29.3k ⢠19 -
NexaAI/Qwen3-VL-8B-Thinking-GGUF
Image-Text-to-Text ⢠8B ⢠Updated ⢠14.8k ⢠13
Latest SOTA models supported on Qualcomm NPU.
Nexa AI infra to support Qwen3VL running on GPU/NPU/CPU
-
NexaAI/Qwen3-VL-4B-Instruct-GGUF
Image-Text-to-Text ⢠4B ⢠Updated ⢠25.4k ⢠25 -
NexaAI/Qwen3-VL-4B-Thinking-GGUF
Image-Text-to-Text ⢠4B ⢠Updated ⢠7.57k ⢠6 -
NexaAI/Qwen3-VL-8B-Instruct-GGUF
Image-Text-to-Text ⢠8B ⢠Updated ⢠29.3k ⢠19 -
NexaAI/Qwen3-VL-8B-Thinking-GGUF
Image-Text-to-Text ⢠8B ⢠Updated ⢠14.8k ⢠13
spaces
5
Running
64
Nexa Omni Demo
đ§
Generate text from audio input
Running
79
Omnivlm Dpo Demo
đ
Ask questions about images and get detailed answers
Running
on
CPU Upgrade
30
Open LLM Leaderboard for domains
đ
Ranking for Open-sourced LLMs in different domains
Running
on
CPU Upgrade
37
Nexa AI GGUF Convertor
âĄ
Submit a model for quantization and receive an email notification
models
84
NexaAI/Qwen3-8B-NPU
Updated
NexaAI/Granite-4.0-h-350M-NPU
Updated
â˘
22
â˘
1
NexaAI/Qwen3-VL-2B-Instruct-GGUF
2B
â˘
Updated
â˘
5.92k
â˘
15
NexaAI/Qwen3-VL-2B-Thinking-GGUF
2B
â˘
Updated
â˘
2.09k
â˘
12
NexaAI/Qwen3-VL-8B-Thinking-GGUF
Image-Text-to-Text
â˘
8B
â˘
Updated
â˘
14.8k
â˘
13
NexaAI/Qwen3-VL-8B-Instruct-GGUF
Image-Text-to-Text
â˘
8B
â˘
Updated
â˘
29.3k
â˘
19
NexaAI/Qwen3-VL-4B-Thinking-GGUF
Image-Text-to-Text
â˘
4B
â˘
Updated
â˘
7.57k
â˘
6
NexaAI/Qwen3-VL-4B-Instruct-GGUF
Image-Text-to-Text
â˘
4B
â˘
Updated
â˘
25.4k
â˘
25
NexaAI/LFM2-1.2B-npu
Updated
â˘
10
â˘
1
NexaAI/Qwen3-VL-4B-Instruct-NPU
Image-Text-to-Text
â˘
0.4B
â˘
Updated
â˘
1.73k