Converted with RKLLM Toolkit v1.2.3 (language model) and RKNN Toolkit (vision encoder). This is a multimodal vision-language model — it accepts both images and text as input.

Key Details

Property	Value
Base Model	Qwen/Qwen3-VL-4B-Instruct
Toolkit Version	RKLLM Toolkit v1.2.3 / RKNN Toolkit
Runtime Version	RKLLM Runtime ≥ v1.2.1 + RKNN Runtime
Quantization	w8a8 (8-bit weights, 8-bit activations)
Target Platform	RK3588
NPU Cores	3
Thinking Mode	❌ Disabled
Model Type	Vision-Language (VLM)
Languages	English, Chinese (multilingual)

Why This Model?

Qwen3-VL-4B-Instruct is Alibaba's 4B vision-language model. It handles image understanding, visual QA, document analysis, and chart reading with strong multilingual support. Running on the RK3588 NPU enables fully local, GPU-free multimodal inference.

Compared to the smaller Qwen3-VL-2B, the 4B variant offers meaningfully better image understanding and text extraction.

Hardware Tested

Orange Pi 5 Plus — RK3588, 16GB RAM, Armbian Linux
RKNPU driver 0.9.8
RKLLM Runtime v1.2.3

Usage

With the RKLLM API Server (VLM mode)

bash

mkdir -p ~/models/qwen3-vl-4b
cd ~/models/qwen3-vl-4b
git lfs install && git clone https://huggingface.co/GatekeeperZA/Qwen3-VL-4B-Instruct-RKLLM-v1.2.3 .

Use with GatekeeperZA/RKLLM-API-Server — the server loads both the .rkllm and .rknn files automatically when placed in the same directory.

File Listing

File	Description
`qwen3-vl-4b-instruct_w8a8_rk3588.rkllm`	Language model weights for RK3588 NPU
`qwen3-vl-4b-vision_rk3588.rknn`	Vision encoder for RK3588 NPU

Compatibility Notes

Minimum runtime: RKLLM Runtime v1.2.1 + RKNN Runtime v2.x. v1.2.3 recommended.
RKNPU driver: ≥ 0.9.6
SoCs: RK3588 / RK3588S. Not compatible with RK3576 without reconversion.
RAM: ~5.5GB loaded. Requires 8GB+ board (16GB recommended).

Acknowledgements

Alibaba Qwen Team for Qwen3-VL
Rockchip / airockchip for the RKLLM and RKNN toolkits
Converted by GatekeeperZA