Nexa quantized models for edge inference
Nexa AI
company
AI & ML interests
on-device multimodal models, on-device inference acceleration, open-source community building
Recent Activity
Organization Card
Welcome to Nexa AI! We specialize in developing advanced on-device AI agents designed to operate seamlessly and efficiently without the need for constant cloud connectivity. Our technology empowers devices to make intelligent decisions locally, enhancing user privacy and device functionality.
For more information, please visit our website! https://nexa.ai/. You can join our waitlist to get the latest progress.
Collections
2
spaces
5
Running
64
Nexa Omni Demo
🎧
Generate text from audio input
Running
78
Omnivlm Dpo Demo
👁
Upload images and get detailed descriptions
Running
6
Dolphin
📈
Answer questions using Qwen or Dolphin AI models
Runtime error
29
Open LLM Leaderboard for domains
📊
Ranking for Open-sourced LLMs in different domains
Running
on
CPU Upgrade
31
Nexa AI GGUF Convertor
⚡
Request custom GGML quantized models via email
models
16
NexaAIDev/DeepSeek-R1-Distill-Llama-8B-NexaQuant
Updated
•
189
•
88
NexaAIDev/DeepSeek-R1-Distill-Qwen-1.5B-NexaQuant
Updated
•
222
•
91
NexaAIDev/OmniVLM-968M
Updated
•
1.31k
•
516
NexaAIDev/OmniAudio-2.6B
Audio-Text-to-Text
•
Updated
•
1.15k
•
265
NexaAIDev/Qwen2-Audio-7B-GGUF
Audio-Text-to-Text
•
Updated
•
5k
•
153
NexaAIDev/Squid
Updated
•
42
•
34
NexaAIDev/gemma-2-2b-it-GGUF
Text Generation
•
Updated
•
324
•
5
NexaAIDev/octo-planner-gguf
Text Generation
•
Updated
•
107
•
4
NexaAIDev/octo-planner-2b
Text Generation
•
Updated
•
36
•
10
NexaAIDev/octopus-planning
Text Generation
•
Updated
•
16
•
20