---
title: README
emoji: 🏆
colorFrom: gray
colorTo: yellow
sdk: gradio
pinned: false
sdk_version: 5.33.1
---

# AXera Models Research

This is the home for Axera's npu model(axmodel) and npu's tools (Pulsar2). We released(such as):

- [MiniCPM4](https://huggingface.co/collections/AXERA-TECH/minicpm4-6849c10a9d4a2872b68fdd4e) : MiniCPM4-0.5B
- [Qwen3](https://huggingface.co/collections/AXERA-TECH/qwen3-680f5340589f4c2bf6959cc3) : Qwen3-0.6B, Qwen3-1.7B, Qwen3-4B
- [Qwen2.5](https://huggingface.co/collections/AXERA-TECH/qwen25-67b0bdab7417cc593ed50c84) : Qwen2.5-0.5B, Qwen2.5-1.5B, Qwen2.5-3B, Qwen2.5-7B
- [DeepSeek](DeepSeek-R1-Distill)
- [HuggingFaceTB](https://huggingface.co/collections/AXERA-TECH/huggingfacetb-67caf2fbf7d505f443ac9b3d) : SmolLM, SmolVLM
- [Multimodal Models](https://huggingface.co/collections/AXERA-TECH/multimodal-models-67b0befd36aa53b5903d351d) : CLIP, StableDiffusion, Qwen2.5-VL-3B, InternelVL3-2B, Janus-Pro-1B 
- [Vision Models](https://huggingface.co/collections/AXERA-TECH/vision-models-67b0bce92ddc61229e8e94ed) : Ultralytics, Depth-Anything-V2, MixFormerV2, LivePortrait, Real-ESRGAN 
- [Audio Models](https://huggingface.co/collections/AXERA-TECH/audio-models-67b0be1788060c5a7c40af89) : Whisper, SenseVoice, MeloTTS, Demucs
- [Tools](https://huggingface.co/collections/AXERA-TECH/tools-67c976cdfbe890fb30c3aadb) : Pulsar2

Other 

- [AXERA on GitHub](https://github.com/AXERA-TECH)