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/Qwen3.5-2B
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)	Qwen3.5-2B_RK3576_w4a16_g128.rkllm	`76f40bbbc559615767e49a9408d28a1afc16c3a12aa3764a11e13f52acd868e9`	Qwen3.5-2B_vision_RK3576.rknn	`c752c9ddec5ad0415cff7d5b2cd645c00273d7f75cfb034182126309911c051b`
RK3576	W8A8	Qwen3.5-2B_RK3576_w8a8.rkllm	`95f4c10bf5d8880a4697c9c4e06508559930a9e379c4b154012daa94018ce8ae`	Qwen3.5-2B_vision_RK3576.rknn	`c752c9ddec5ad0415cff7d5b2cd645c00273d7f75cfb034182126309911c051b`
RK3588	W8A8	Qwen3.5-2B_RK3588_w8a8.rkllm	`946daf4377bbf5913d8d5226180991b8e6b4a3068d8b5959bdc81a9492311a09`	Qwen3.5-2B_vision_RK3588.rknn	`9077bfd3f4a0a3846af7fd1609175aaaba07858d00acdc31459ae9f2dc66716a`

The root Qwen3.5-2B_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/Qwen3.5-2B-RKLLM \
  RK3576/Qwen3.5-2B_RK3576_w4a16_g128.rkllm \
  RK3576/Qwen3.5-2B_vision_RK3576.rknn \
  --local-dir Qwen3.5-2B-RKLLM

Use them with the RKLLM VLM runtime. For a Docker API, see 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.