Upload README.md

README.md

@@ -7,6 +7,11 @@ tags:
 - prerouter
 - lora
 - ssd-offload
+- multi-platform
+- ios
+- android
+- windows
+- macos
 base_model:
 - inclusionAI/Ling-3.0-tiny-base
 pipeline_tag: text-generation
@@ -22,6 +27,8 @@ pipeline_tag: text-generation
 
 **1 GiB active memory · 25 tok/s · 4-bit**
 
+**Native engines on iOS · macOS · Android · Windows.**
+
 [![GitHub](https://img.shields.io/badge/GitHub-Edge0--AI%2Fedge0-black?style=for-the-badge&logo=github)](https://github.com/Edge0-AI/edge0)
 [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Edge0--35b--a3b--preview-yellow?style=for-the-badge)](https://huggingface.co/Edge0/Edge0-35b-a3b-preview)
 [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Edge0--8b--a1b--preview-yellow?style=for-the-badge)](https://huggingface.co/Edge0/Edge0-8b-a1b-preview)
@@ -30,6 +37,11 @@ pipeline_tag: text-generation
 [![arXiv](https://img.shields.io/badge/arXiv-2609.18063-B31B1B?style=for-the-badge&logo=arxiv&logoColor=white)](https://arxiv.org/abs/2609.18063)
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue?style=for-the-badge)](https://github.com/Edge0-AI/edge0/blob/main/LICENSE)
 
+[![iOS](https://img.shields.io/badge/iOS-000000?style=for-the-badge&logo=apple&logoColor=white)](https://github.com/Edge0-AI/edge0/tree/main/ios)
+[![macOS](https://img.shields.io/badge/macOS-000000?style=for-the-badge&logo=apple&logoColor=white)](https://github.com/Edge0-AI/edge0/tree/main/macos)
+[![Android](https://img.shields.io/badge/Android-3DDC84?style=for-the-badge&logo=android&logoColor=black)](https://github.com/Edge0-AI/edge0/tree/main/android)
+[![Windows](https://img.shields.io/badge/Windows-0078D6?style=for-the-badge&logo=windows11&logoColor=white)](https://github.com/Edge0-AI/edge0/tree/main/windows)
+
 </div>
 
 
@@ -53,8 +65,36 @@ via the [edge0](https://github.com/Edge0-AI/edge0) streaming inference framework
 
 </div>
 
+## Platforms — one model, four native engines
+
+<div align="center">
+
+**On 2026-09-30 we released the edge0 inference engines for
+four platforms — so users get the best inference experience across
+architectures and platforms. The source is open-sourced in the
+[edge0 repo](https://github.com/Edge0-AI/edge0).**
+
+| Platform | Native engine (open source) |
+|---|---|
+| 📱 **iOS** | [edge0/ios](https://github.com/Edge0-AI/edge0/tree/main/ios) |
+| 🖥️ **macOS** | [edge0/macos](https://github.com/Edge0-AI/edge0/tree/main/macos) |
+| 🤖 **Android** | [edge0/android](https://github.com/Edge0-AI/edge0/tree/main/android) |
+| 🪟 **Windows** | [edge0/windows](https://github.com/Edge0-AI/edge0/tree/main/windows) |
+
+</div>
+
+This checkpoint is built for all of them: one model directory — the same
+int4 base plus LoRA / prerouter adapters — runs unchanged on every
+platform, so what you download here is what ships on a phone, a desktop
+and a laptop alike.
+
 ## Highlights
 
+- **Runs on iOS, macOS, Android and Windows**: the edge0 inference
+  engines are **open-source and native on all four platforms** — one
+  model, the best inference experience on every architecture and
+  platform (see [Platforms](#platforms--one-model-four-native-engines)
+  below).
 - **Runs in phone-class memory**: the full 4-bit checkpoint stays on
   storage and experts are streamed on demand, so only the active
   weights are in RAM — under **1 GiB**, with no sharding and no
@@ -143,8 +183,10 @@ Measured with `examples/bench.py` on a Mac mini M4 Pro, 24 GB:
   agentic tasks — tool use, multi-step planning, and long-horizon
   autonomy are currently weak. The full release will substantially
   strengthen agent capability.
-- The MLX backend currently targets Apple Silicon; other backends are
-  on the edge0 roadmap.
+- Platform coverage: the performance numbers above are measured with
+  the MLX backend on Apple Silicon; engine coverage and tuning on the
+  iOS / Android / Windows engines are still maturing (see
+  [Platforms](#platforms--one-model-four-native-engines)).
 
 ## Quick start