| --- |
| license: apache-2.0 |
| base_model: Qwen/Qwen2-0.5B-Instruct |
| pipeline_tag: text-generation |
| library_name: rkllm |
| tags: |
| - rkllm |
| - rockchip |
| - rk3576 |
| - rk3588 |
| - qwen |
| - qwen2 |
| --- |
| |
| # Qwen2-0.5B-Instruct · RKLLM |
|
|
| Text generation on Rockchip RK3576 and RK3588, converted from [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct). |
|
|
| - **Conversion toolkit:** RKLLM Toolkit 1.3.0. |
| - **Inputs / output:** text → text. |
| - **License:** `apache-2.0`; the [upstream model card](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) describes its terms and intended use. |
|
|
| ## Choose your files |
|
|
| Use the files for your board’s exact SoC. `w4a16` uses 4-bit weights and 16-bit activations; `w4a16_g128` adds a weight group size of 128. `w8a8` uses 8-bit weights and activations. File size below is download size, not total runtime RAM. |
|
|
| | Board | Quantization | Size | Language model | |
| | --- | --- | --- | --- | |
| | RK3576 | `w4a16_g128` | 0.64 GiB | [Qwen2-0.5B-Instruct_RK3576_w4a16_g128.rkllm](RK3576/Qwen2-0.5B-Instruct_RK3576_w4a16_g128.rkllm) | |
| | RK3576 | `w8a8` | 0.76 GiB | [Qwen2-0.5B-Instruct_RK3576_w8a8.rkllm](RK3576/Qwen2-0.5B-Instruct_RK3576_w8a8.rkllm) | |
| | RK3588 | `w8a8` | 0.75 GiB | [Qwen2-0.5B-Instruct_RK3588_w8a8.rkllm](RK3588/Qwen2-0.5B-Instruct_RK3588_w8a8.rkllm) | |
|
|
| ## Run on your board |
|
|
| With Docker installed on a matching Rockchip board, this example starts the **RK3576 w4a16_g128** model and its API on port 8001: |
| |
| ```bash |
| sudo docker run --rm -d --name rkllm \ |
| --privileged -v /dev:/dev -p 8001:8001 \ |
| ghcr.io/hanzo-huang/rkllm-docker/llm/qwen2-0.5b-instruct:rk3576-w4a16-g128 |
| ``` |
| |
| The image includes its model file. See [rkllm-docker](https://github.com/Hanzo-Huang/rkllm-docker#readme) for API requests, other board variants, and configuration. |
| |
| To download the files separately instead: |
| |
| ```bash |
| hf download HanzoHuang/Qwen2-0.5B-Instruct-RKLLM \ |
| RK3576/Qwen2-0.5B-Instruct_RK3576_w4a16_g128.rkllm \ |
| --local-dir ./models |
| ``` |
| |
| These are native RKLLM/RKNN artifacts. Use a compatible RKLLM runtime and the model’s correct chat template when integrating them in another application. |
| |
| ## Release notes |
| |
| No per-variant board benchmark is published here. Quantized output may differ from the original model; check responses on your own workloads. Use the toolkit version listed above when checking runtime compatibility. |
| |
| <details> |
| <summary>SHA-256 checksums</summary> |
| |
| ```text |
| a166cdcff5d8a2e33423d01d8bac6f7a6ad1e1130fbd0bfefdb8b69082113e87 RK3576/Qwen2-0.5B-Instruct_RK3576_w4a16_g128.rkllm |
| cdccb51e23131352823af8becf9ac4acb15cb30f0f961e89d16cb0fabd003414 RK3576/Qwen2-0.5B-Instruct_RK3576_w8a8.rkllm |
| 24e99eeea1512d6e7f3f120f3344a510933301dfcb72bd64b24a9724ab48e1d8 RK3588/Qwen2-0.5B-Instruct_RK3588_w8a8.rkllm |
| ``` |
| |
| </details> |
| |
| ## Credits |
| |
| Original model: [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct). Conversion tools: [Rockchip RKLLM](https://github.com/airockchip/rknn-llm). |
| |
