These hardware-specific .rkllm files require a compatible Rockchip RKLLM runtime. They are not Transformers checkpoints and cannot be loaded directly with Transformers, llama.cpp, or Ollama.

Base model

Upstream model: Qwen/Qwen3-1.7B
License: Apache-2.0
Model type: LLM (text only)

Conversion and variants

Toolkit version

RKLLM Toolkit: v1.3.0

Use a file built for the exact target SoC.

Target	Quantization	File	SHA256
RK3576	W4A16	Qwen3-1.7B_RK3576_w4a16.rkllm	`9f5f2facdef5f1da27756524f0284b307d5e4cee45ae9d9c8a02b6e9d8888ce2`
RK3576	W4A16 (g128)	Qwen3-1.7B_RK3576_w4a16_g128.rkllm	`c72954ad5bd155aa49f89a86cb2133b79fafd502685d345973e26bb07a9c14a7`
RK3576	W8A8	Qwen3-1.7B_RK3576_w8a8.rkllm	`2d1c1ec4e50a9edb85b801f546d935943481e7671d3a73d19a2df9f18d4da2ca`
RK3588	W8A8	Qwen3-1.7B_RK3588_w8a8.rkllm	`384294b54bf68b61590c4d818c33e27d67dbeced51fb9f1f93014f0ad06d2545`

The repository also includes Qwen3-1.7B_data_quant.json, used as calibration data during conversion.

Usage

bash

hf download HanzoHuang/Qwen3-1.7B-RKLLM \
  RK3576/Qwen3-1.7B_RK3576_w4a16_g128.rkllm \
  --local-dir Qwen3-1.7B-RKLLM

Use the Qwen3 chat template with the RKLLM runtime. For Docker deployment, see Hanzo-Huang/rkllm-docker.

Limitations

These are target-specific converted artifacts. Validate quality, memory use, and runtime compatibility on your own Rockchip device.

Acknowledgements

Thanks to the Qwen Team, Rockchip, and the RKLLM community.