Platform Support Matrix
Supported platforms, devices, chipsets, and model formats for ZETIC Melange.
This page lists the platforms, chipsets, model formats, and minimum requirements supported by ZETIC Melange.
Supported Platforms
| Feature | Android | iOS |
|---|---|---|
General model inference (ZeticMLangeModel) | Yes | Yes |
LLM inference (ZeticMLangeLLMModel) | Yes | Yes |
| NPU acceleration | Yes | Yes |
| GPU acceleration | Yes | Yes |
| CPU fallback | Yes | Yes |
| Performance-Adaptive Deployment | Yes | Yes |
Minimum OS Versions
| Platform | Minimum Version |
|---|---|
| Android | API 24 (Android 7.0 Nougat) |
| iOS | 15.0 |
NPU Support by Chipset
Melange automatically compiles and optimizes models for the following NPU architectures:
Qualcomm Snapdragon
| Chipset | NPU | Status |
|---|---|---|
| Snapdragon 8 Gen 3 | Hexagon | Supported |
| Snapdragon 8 Gen 2 | Hexagon | Supported |
| Snapdragon 8 Gen 1 | Hexagon | Supported |
| Snapdragon 888 | Hexagon | Supported |
| Snapdragon 7 Gen 3 | Hexagon | Supported |
| Snapdragon 7 Gen 1 | Hexagon | Supported |
| Snapdragon 6 Gen 1 | Hexagon | Supported |
Google Pixel (Tensor)
| Chipset | NPU | Status |
|---|---|---|
| Tensor G4 | Edge TPU | Enterprise Only |
| Tensor G3 | Edge TPU | Enterprise Only |
| Tensor G2 | Edge TPU | Enterprise Only |
MediaTek Dimensity
| Chipset | NPU | Status |
|---|---|---|
| Dimensity 9300 | APU | Enterprise Only |
| Dimensity 9200 | APU | Enterprise Only |
| Dimensity 8300 | APU | Enterprise Only |
| Dimensity 7200 | APU | Enterprise Only |
Samsung Exynos
| Chipset | NPU | Status |
|---|---|---|
| Exynos 2400 | NPU | Enterprise Only |
| Exynos 2200 | NPU | Enterprise Only |
Google Pixel (Tensor), MediaTek Dimensity, and Samsung Exynos NPU support are available for enterprise customers only. Contact us for enterprise pricing and access.
Apple Silicon
| Chipset | NPU | Status |
|---|---|---|
| A17 Pro | Apple Neural Engine | Supported |
| A16 Bionic | Apple Neural Engine | Supported |
| A15 Bionic | Apple Neural Engine | Supported |
| M-series (iPad) | Apple Neural Engine | Supported |
The chipset support list is continuously expanding. If your target device is not listed here, Melange will still work using GPU or CPU fallback. Contact us for specific chipset inquiries.
Supported Model Formats
| Format | Extension | Status | Notes |
|---|---|---|---|
| ONNX | .onnx | Recommended | Broadest compatibility, supports models from TensorFlow, PyTorch, and other frameworks |
| PyTorch Exported Program | .pt2 | Recommended | Native PyTorch 2.0+ export format with full graph capture |
Input Format
All model inputs must be provided as NumPy arrays (.npy files) during the upload step. These sample inputs are used for:
- Defining fixed input shapes for NPU compilation
- Running accuracy validation during the benchmark phase
- Generating optimized model binaries
NPU compilation hard-codes input shapes to maximize throughput. Even if your original model supports dynamic sizes, the accelerated Melange model will accept only the exact shape of the sample input provided during upload.
SDK Distribution
The Android and iOS package versions below refer to the planned 1.13.0 release. The Flutter package has its own version and currently pins native SDK 1.11.0.
| Platform | Distribution Method | Package |
|---|---|---|
| Android | GitHub Releases (Gradle Ivy repository; setup) | com.zeticai.mlange:mlange:1.13.0 |
| iOS | Swift Package Manager (SPM) | ZeticMLange 1.13.0 |
| Flutter | pub.dev | zetic_mlange: ^1.13.1 (Android/iOS native SDK 1.13.1) |
Robotics and Edge Compute
Beyond phones, Melange compiles ONNX models into accelerated engines for NVIDIA Jetson Thor, with Python and C++ SDKs for the device. This lane has its own upload format and scorecard — see Physical AI. It is available through the ZETIC Early Access Program; contact us to request access.
Next Steps
- Supported Model Formats: Get your model ready for upload
- Quick Start: Deploy your first model
- Changelog: Latest SDK updates and version history
- Migration Guide: Migrating from MLange to Melange naming