README.md

---
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, SmolVLM2
- [Multimodal Models](https://huggingface.co/collections/AXERA-TECH/multimodal-models-67b0befd36aa53b5903d351d) : CLIP, JinaCLIP, StableDiffusion, Qwen3-VL-2B/4B, Qwen2.5-VL-3B/7B, InternelVL3-1B/2B, Janus-Pro-1B, MiniCPM4-V 
- [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, CosyVoice2, MeloTTS, FireRed-AED, SileroVAD, Kokoro

Solution

- [Frigate NVR](https://huggingface.co/AXERA-TECH/frigate-resource) : AI NVR solution, support AX650 and AXCL
- [Immich](https://huggingface.co/AXERA-TECH/immich) : High performance self-hosted photo and video management solution

Tools

- [Pulsar2](https://huggingface.co/AXERA-TECH/Pulsar2) : The NPU Toolchain for AX650/AX8850, AX630C/AX620Q, AX615, AX637
- [AXCL](https://huggingface.co/AXERA-TECH/AXCL)：The driver install package for AX650/AX8850
- [PPQ-XS](https://huggingface.co/AXERA-TECH/ppq-xs) : The NPU Toolchain for AX520/AX513

Other 

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