| --- |
| 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 |
|
|
| * Max context length: 4096 |
|
|
| Image and text on Rockchip RK3576 and RK3588, converted from [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B). |
|
|
| - **Conversion toolkit:** RKLLM Toolkit 1.3.0. |
| - **Inputs / output:** text or image + text → text. |
| - **License:** `apache-2.0`; the [upstream model card](https://huggingface.co/Qwen/Qwen3.5-4B) describes its terms and intended use. |
|
|
| ## Choose your files |
|
|
| Use the files for your board’s exact SoC. `w4a16` uses 4-bit weights and 16-bit activations; `w4a16_g128` adds a weight group size of 128. `w8a8` uses 8-bit weights and activations. File size below is download size, not total runtime RAM. |
|
|
| | Board | Quantization | Size | Language model | |
| | --- | --- | --- | --- | |
| | RK3576 | `w4a16_g128` | 3.71 GiB | [Qwen3.5-4B_RK3576_w4a16_g128.rkllm](RK3576/Qwen3.5-4B_RK3576_w4a16_g128.rkllm) | |
| | RK3576 | `w8a8` | 5.18 GiB | [Qwen3.5-4B_RK3576_w8a8.rkllm](RK3576/Qwen3.5-4B_RK3576_w8a8.rkllm) | |
| | RK3588 | `w8a8` | 5.16 GiB | [Qwen3.5-4B_RK3588_w8a8.rkllm](RK3588/Qwen3.5-4B_RK3588_w8a8.rkllm) | |
|
|
| For image input, also download the **vision encoder for the same SoC**. Keep the language model and vision encoder from this release together. |
|
|
| | Board | Size | Vision encoder | |
| | --- | --- | --- | |
| | RK3576 | 0.68 GiB | [Qwen3.5-4B_vision_RK3576.rknn](RK3576/Qwen3.5-4B_vision_RK3576.rknn) | |
| | RK3588 | 0.66 GiB | [Qwen3.5-4B_vision_RK3588.rknn](RK3588/Qwen3.5-4B_vision_RK3588.rknn) | |
|
|
| ONNX files are export intermediates; they are not needed to run these RKNN/RKLLM models. |
|
|
| ## Run on your board |
|
|
| With Docker installed on a matching Rockchip board, this example starts the **RK3576 w4a16_g128** model and its API on port 8001: |
| |
| ```bash |
| sudo docker run --rm -d --name rkllm \ |
| --privileged -v /dev:/dev -p 8001:8001 \ |
| ghcr.io/hanzo-huang/rkllm-docker/vlm/qwen3.5-4b:rk3576-w4a16-g128 |
| ``` |
| |
| The image includes its model files. See [rkllm-docker](https://github.com/Hanzo-Huang/rkllm-docker#readme) for API requests, image inputs, other board variants, and configuration. |
| |
| To download the files separately instead: |
| |
| ```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 ./models |
| ``` |
| |
| These are native RKLLM/RKNN artifacts. Use a compatible RKLLM runtime and the model’s correct chat template when integrating them in another application. |
| |
| ## Release notes |
| |
| No per-variant board benchmark is published here. Quantized output may differ from the original model; check responses on your own workloads. Use the toolkit version listed above when checking runtime compatibility. |
| |
| <details> |
| <summary>SHA-256 checksums</summary> |
| |
| ```text |
| aa4d34b42752a0e491ed891ce4b7f32a745631601a65b175f743f971bdb33482 RK3576/Qwen3.5-4B_RK3576_w4a16_g128.rkllm |
| 736f4b1065b481bae9cbd86e6c9ed30222abba9c5a3cb2d8d68dd92037d82dfe RK3576/Qwen3.5-4B_RK3576_w8a8.rkllm |
| 715566bbee72b25d8c4912f6cf6256a8ac264a754511573a99a541487bbc06b4 RK3588/Qwen3.5-4B_RK3588_w8a8.rkllm |
| 6692f52adaa7ee0ba892c7cbba01979750cb82cff8061a571f56e9d84c6d98a2 RK3576/Qwen3.5-4B_vision_RK3576.rknn |
| c286ef69266c11a2a2cedd881ad6a40415c17c8924962f07454359bb6d60e2ba RK3588/Qwen3.5-4B_vision_RK3588.rknn |
| ``` |
| |
| </details> |
| |
| ## Credits |
| |
| Original model: [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B). Conversion tools: [Rockchip RKLLM](https://github.com/airockchip/rknn-llm). |
| |
