| --- |
| 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/RKNN-converted Qwen3.5-4B multimodal artifacts for Rockchip RK3576 and RK3588 NPUs. |
|
|
| This is a VLM conversion: each supported platform requires both the `.rkllm` language model and the matching `.rknn` vision encoder. The pair must come from the same platform directory. These are hardware-specific artifacts, not Transformers checkpoints. |
|
|
| ## Base model |
|
|
| - Upstream model: [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) |
| - License: Apache-2.0 |
| - Model type: VLM (vision-language model) |
|
|
| ## Conversion and variants |
|
|
| ### Toolkit version |
|
|
| **RKLLM Toolkit: v1.3.0** · **RKNN vision conversion: paired `.rknn` encoder** |
|
|
| Use a matching pair for the exact target SoC. |
|
|
| | Target | Quantization | RKLLM language model | RKLLM SHA256 | RKNN vision encoder | RKNN SHA256 | |
| | --- | --- | --- | --- | --- | --- | |
| | RK3576 | W4A16 (g128) | [Qwen3.5-4B_RK3576_w4a16_g128.rkllm](RK3576/Qwen3.5-4B_RK3576_w4a16_g128.rkllm) | `aa4d34b42752a0e491ed891ce4b7f32a745631601a65b175f743f971bdb33482` | [Qwen3.5-4B_vision_RK3576.rknn](RK3576/Qwen3.5-4B_vision_RK3576.rknn) | `6692f52adaa7ee0ba892c7cbba01979750cb82cff8061a571f56e9d84c6d98a2` | |
| | RK3576 | W8A8 | [Qwen3.5-4B_RK3576_w8a8.rkllm](RK3576/Qwen3.5-4B_RK3576_w8a8.rkllm) | `736f4b1065b481bae9cbd86e6c9ed30222abba9c5a3cb2d8d68dd92037d82dfe` | [Qwen3.5-4B_vision_RK3576.rknn](RK3576/Qwen3.5-4B_vision_RK3576.rknn) | `6692f52adaa7ee0ba892c7cbba01979750cb82cff8061a571f56e9d84c6d98a2` | |
| | RK3588 | W8A8 | [Qwen3.5-4B_RK3588_w8a8.rkllm](RK3588/Qwen3.5-4B_RK3588_w8a8.rkllm) | `715566bbee72b25d8c4912f6cf6256a8ac264a754511573a99a541487bbc06b4` | [Qwen3.5-4B_vision_RK3588.rknn](RK3588/Qwen3.5-4B_vision_RK3588.rknn) | `c286ef69266c11a2a2cedd881ad6a40415c17c8924962f07454359bb6d60e2ba` | |
|
|
| The root `Qwen3.5-4B_vision.onnx` is the vision conversion input; use the platform-specific `.rknn` encoder for deployment. |
|
|
| ## Usage |
|
|
| Download both files for the target platform: |
|
|
| ```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 |
| ``` |
|
|
| Use them with the RKLLM VLM runtime. For a Docker API, see [Hanzo-Huang/rkllm-docker](https://github.com/Hanzo-Huang/rkllm-docker) and set `MODEL_KIND=vlm` with both model files. |
|
|
| ## Limitations |
|
|
| The vision encoder and language model are SoC-specific and must be kept as a matching pair. Validate image preprocessing, memory use, and runtime compatibility on your device. |
|
|
| ## Acknowledgements |
|
|
| Thanks to the Qwen Team, Rockchip, and the RKLLM/RKNN community. |
|
|
