| --- |
| license: mit |
| base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B |
| pipeline_tag: text-generation |
| library_name: rkllm |
| tags: |
| - rkllm |
| - rockchip |
| - rk3576 |
| - rk3588 |
| - deepseek |
| - deepseek-r1 |
| - qwen |
| --- |
| |
| # 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](https://huggingface.co/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](RK3576/DeepSeek-R1-Distill-Qwen-1.5B_RK3576_w4a16_g128.rkllm) | `e737c9aa8cfbfd0216e547ed67bc2325d5add2f8b2aa21037389e296ac3b8d80` | |
| | RK3576 | W8A8 | [DeepSeek-R1-Distill-Qwen-1.5B_RK3576_w8a8.rkllm](RK3576/DeepSeek-R1-Distill-Qwen-1.5B_RK3576_w8a8.rkllm) | `6ceab2c6b93a8b55837ab75e4050bbce888030153c0bc83a465bd73ead44120f` | |
| | RK3588 | W8A8 | [DeepSeek-R1-Distill-Qwen-1.5B_RK3588_w8a8.rkllm](RK3588/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 |
|
|
| ```bash |
| 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](https://github.com/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. |
|
|
