DeepSeek-R1-Distill-Qwen-1.5B-RKLLM

RKLLM-converted DeepSeek-R1-Distill-Qwen-1.5B language-model artifacts for Rockchip RK3576 and RK3588 NPUs.

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: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
• License: MIT
• 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-g128	DeepSeek-R1-Distill-Qwen-1.5B_RK3576_w4a16_g128.rkllm	e737c9aa8cfbfd0216e547ed67bc2325d5add2f8b2aa21037389e296ac3b8d80
RK3576	W8A8	DeepSeek-R1-Distill-Qwen-1.5B_RK3576_w8a8.rkllm	6ceab2c6b93a8b55837ab75e4050bbce888030153c0bc83a465bd73ead44120f
RK3588	W8A8	DeepSeek-R1-Distill-Qwen-1.5B_RK3588_w8a8.rkllm	d00038d619c1905ac66ab5d499019d80889d37cc1f81be491cc503e284950c2d

The repository also includes DeepSeek-R1-Distill-Qwen-1.5B_data_quant.json, used as calibration data during conversion.

Usage

hf download HanzoHuang/DeepSeek-R1-Distill-Qwen-1.5B-RKLLM \
  RK3576/DeepSeek-R1-Distill-Qwen-1.5B_RK3576_w4a16_g128.rkllm \
  --local-dir DeepSeek-R1-Distill-Qwen-1.5B-RKLLM

Use the upstream DeepSeek R1 chat template with the RKLLM runtime. For Docker deployment, see Hanzo-Huang/rkllm-docker.

Limitations

These are target-specific converted artifacts. Quantization and conversion can change output quality relative to the upstream model; validate the result on your Rockchip device.

Acknowledgements

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