Add complete model card

README.md

@@ -1,3 +1,62 @@
 ---
 license: apache-2.0
+base_model: Qwen/Qwen3.5-4B
+pipeline_tag: image-text-to-text
+library_name: rkllm
+tags:
+- rkllm
+- rockchip
+- rk3576
+- rk3588
+- qwen
+- qwen3.5
+- multimodal
 ---
+
+# Qwen3.5-4B-RKLLM
+
+RKLLM-converted Qwen3.5-4B artifacts for deployment on Rockchip RK3576 and RK3588 NPUs. This repository includes language-model binaries and the matching vision encoder artifacts for multimodal inference.
+
+`.rkllm` and `.rknn` files require the Rockchip RKLLM/RKNN runtime. They cannot be loaded directly with Transformers, llama.cpp, or Ollama.
+
+## Base Model
+
+- Model: Qwen3.5-4B
+- Author: Qwen Team
+- Original model: [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B)
+- Original license: Apache-2.0
+
+Refer to the upstream model card for the original model's capabilities, limitations, and acceptable-use guidance.
+
+## Available Artifacts
+
+| Target | Language model | Quantization | Vision model |
+| --- | --- | --- | --- |
+| RK3576 | [`Qwen3.5-4B_RK3576_w4a16_g128.rkllm`](RK3576/Qwen3.5-4B_RK3576_w4a16_g128.rkllm) | W4A16 (g128) | [`Qwen3.5-4B_vision_RK3576.rknn`](RK3576/Qwen3.5-4B_vision_RK3576.rknn) |
+| RK3576 | [`Qwen3.5-4B_RK3576_w8a8.rkllm`](RK3576/Qwen3.5-4B_RK3576_w8a8.rkllm) | W8A8 | [`Qwen3.5-4B_vision_RK3576.rknn`](RK3576/Qwen3.5-4B_vision_RK3576.rknn) |
+| RK3588 | [`Qwen3.5-4B_RK3588_w8a8.rkllm`](RK3588/Qwen3.5-4B_RK3588_w8a8.rkllm) | W8A8 | [`Qwen3.5-4B_vision_RK3588.rknn`](RK3588/Qwen3.5-4B_vision_RK3588.rknn) |
+
+The repository also contains `Qwen3.5-4B_vision.onnx`, the vision encoder in ONNX format, and `Qwen3.5-4B_data_quant.json`, the calibration data used during conversion.
+
+## Usage
+
+Download one language-model artifact and the matching vision artifact for your SoC. Do not mix RK3576 and RK3588 files.
+
+```bash
+hf download HanzoHuang/Qwen3.5-4B-RKLLM \
+  RK3576/Qwen3.5-4B_RK3576_w4a16_g128.rkllm \
+  RK3576/Qwen3.5-4B_vision_RK3576.rknn \
+  --local-dir Qwen3.5-4B-RKLLM
+```
+
+Load the `.rkllm` model with a compatible RKLLM runtime and the `.rknn` vision encoder with the matching RKNN runtime. Application code must implement Qwen3.5's multimodal preprocessing and prompt format.
+
+## Limitations
+
+- These are hardware-specific converted artifacts, not Transformers checkpoints.
+- Runtime, driver, and toolkit compatibility depends on the Rockchip software stack installed on the device.
+- Conversion may change output quality relative to the upstream floating-point model; validate on your own workload.
+
+## Acknowledgements
+
+Thanks to the Qwen Team for releasing Qwen3.5-4B and to Rockchip and RKLLM contributors for the deployment toolchain.