🤝 Supported chipmakers

NexaSDK is an easy-to-use developer toolkit for running any AI model locally — across NPUs, GPUs, and CPUs — powered by our NexaML engine, built entirely from scratch for peak performance on every hardware stack. Unlike wrappers that depend on existing runtimes, NexaML is a unified inference engine built at the kernel level. It’s what lets NexaSDK achieve Day-0 support for new model architectures (LLMs, multimodal, audio, vision). NexaML supports 3 model formats: GGUF, MLX, and Nexa AI's own .nexa format.

• 📣 Release Nexa AI’s AutoNeural-VL-1.5B, an NPU-native vision–language model built for real-time in-car assistants, delivering 14× lower latency, 3× faster decode, and 4× longer context on Qualcomm SA8295P — now also runnable on Qualcomm X Elite laptops.
• 📣 Support Mistral AI's Ministral-3-3B across Qualcomm Hexagon NPU, Apple Neural Engine, GPU and CPU.
• 📣 Release Linux SDK for NPU/GPU/CPU. See Linux SDK Doc.
• 📣 Support Apple Neural Engine for Granite-4.0, Qwen3, Gemma3, and Parakeetv3. Download NexaSDK for ANE here.
• 📣 Support Android SDK for NPU/GPU/CPU. See Android SDK Doc and Android SDK Demo App.
• 📣 Support SDXL-turbo image generation on AMD NPU. See AMD blog : Advancing AI with Nexa AI.
• Support Android Python SDK for NPU/GPU/CPU. See Android Python SDK Doc and Android Python SDK Demo App.
• 📣 Day-0 Support for Qwen3-VL-4B and 8B in GGUF, MLX, .nexa format for NPU/GPU/CPU. We are the only framework that supports the GGUF format. Featured in Qwen's post about our partnership.
• 📣 Day-0 Support for IBM Granite 4.0 on NPU/GPU/CPU. NexaML engine were featured right next to vLLM, llama.cpp, and MLX in IBM's blog.
• 📣 Day-0 Support for Google EmbeddingGemma on NPU. We are featured in Google's social post.
• 📣 Supported vision capability for Gemma3n: First-ever Gemma-3n multimodal inference for GPU & CPU, in GGUF format.
• 📣 Intel NPU Support DeepSeek-r1-distill-Qwen-1.5B and Llama3.2-3B
• 📣 Apple Neural Engine Support for real-time speech recognition with Parakeet v3 model

• arm64 for Apple Neural Engine
• arm64 for MLX
• x86_64

• arm64 with Qualcomm NPU support
• x86_64 with Intel / AMD NPU support

curl -fsSL https://github.com/NexaAI/nexa-sdk/releases/latest/download/nexa-cli_linux_x86_64.sh -o install.sh && chmod +x install.sh && ./install.sh && rm install.sh

curl -fsSL https://github.com/NexaAI/nexa-sdk/releases/latest/download/nexa-cli_linux_arm64.sh -o install.sh && chmod +x install.sh && ./install.sh && rm install.sh

sudo rm -r /opt/nexa_sdk
sudo rm /usr/local/bin/nexa
# if you want to remove data as well
# rm -r $HOME/.cache/nexa.ai

You can run any compatible GGUF, MLX, or nexa model from 🤗 Hugging Face by using the nexa infer <full repo name>.

📝 Run and chat with LLMs, e.g. Qwen3:

nexa infer ggml-org/Qwen3-1.7B-GGUF

🖼️ Run and chat with Multimodal models, e.g. Qwen3-VL-4B:

nexa infer NexaAI/Qwen3-VL-4B-Instruct-GGUF

📝 Run and chat with LLMs, e.g. Qwen3:

nexa infer NexaAI/Qwen3-4B-4bit-MLX

🖼️ Run and chat with Multimodal models, e.g. Gemma3n:

nexa infer NexaAI/gemma-3n-E4B-it-4bit-MLX

1. Login & Get Access Token (required for Pro Models)

   • Create an account at sdk.nexa.ai
   • Go to Deployment → Create Token
   • Run this once in your terminal (replace with your token):

     nexa config set license '<your_token_here>'

2. Run and chat with our multimodal model, OmniNeural-4B, or other models on NPU

nexa infer NexaAI/OmniNeural-4B
nexa infer NexaAI/Granite-4-Micro-NPU
nexa infer NexaAI/Qwen3-VL-4B-Instruct-NPU

👉 To interact with multimodal models, you can drag photos or audio clips directly into the CLI — you can even drop multiple images at once!

See CLI Reference for full commands.

# hf download <model> --local-dir /path/to/modeldir
nexa pull <model> --model-hub localfs --local-path /path/to/modeldir

Nexa Wishlist — Request and vote for the models you want to run on-device.

Drop a Hugging Face repo ID, pick your preferred backend (GGUF, MLX, or Nexa format for Qualcomm + Apple NPUs), and watch the community's top requests go live in NexaSDK.

👉 Vote now at sdk.nexa.ai/wishlist

We would like to thank the following projects:

• ggml
• mlx-lm
• mlx-vlm
• mlx-audio

Earn up to 1,500 USD for building with NexaSDK.

Learn more in our Participant Details.