Instructions to use HanzoHuang/MiniCPM3-4B-RKLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- RKLLM
How to use HanzoHuang/MiniCPM3-4B-RKLLM with RKLLM:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
English | 简体中文
🚀 Deploy with reComputer AI Lab
Explore and deploy AI models on Rockchip RK3576 and RK3588 devices with reComputer AI Lab.
⚡ Run with one command
With Docker installed, choose your model and board in reComputer AI Lab, copy the deployment command, and run it in your device’s terminal.
Explore Models & Deployment Guides →
MiniCPM3-4B · RKLLM
- Max context length: 4096
Text generation on Rockchip RK3576 and RK3588, converted from openbmb/MiniCPM3-4B.
- Conversion toolkit: RKLLM Toolkit 1.3.0.
- Inputs / output: text → text.
- License:
apache-2.0; the upstream model card 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 |
2.70 GiB | MiniCPM3-4B_RK3576_w4a16_g128.rkllm |
| RK3576 | w8a8 |
4.22 GiB | MiniCPM3-4B_RK3576_w8a8.rkllm |
| RK3588 | w8a8 |
4.20 GiB | MiniCPM3-4B_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:
sudo docker run --rm -d --name rkllm \
--privileged -v /dev:/dev -p 8001:8001 \
ghcr.io/hanzo-huang/rkllm-docker/llm/minicpm3-4b:rk3576-w4a16-g128
The image includes its model file. See rkllm-docker for API requests, other board variants, and configuration.
To download the files separately instead:
hf download HanzoHuang/MiniCPM3-4B-RKLLM \
RK3576/MiniCPM3-4B_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.
SHA-256 checksums
ec05211d17c4bb05a685588ff335608233b59722f6ecc296976d61dbc88c4128 RK3576/MiniCPM3-4B_RK3576_w4a16_g128.rkllm
3795c6a22e5f12de0c4243fc187da55f516b530de3125734874d340856160aec RK3576/MiniCPM3-4B_RK3576_w8a8.rkllm
3815a59593df7aebda90f86844caf2fd625d9d0e996e35aa31fd74790d10b130 RK3588/MiniCPM3-4B_RK3588_w8a8.rkllm
Credits
Original model: openbmb/MiniCPM3-4B. Conversion tools: Rockchip RKLLM.
- Downloads last month
- 83
Model tree for HanzoHuang/MiniCPM3-4B-RKLLM
Base model
openbmb/MiniCPM3-4B