Downloads · 30 days
10
43% of all-time downloads
intent-rk3588-npu
Icerm/intent-rk3588-npu
intent-rk3588-npu is a machine learning model from Icerm. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for rkllm. The card lists the license as apache-2.0.
Pre-converted NPU weights for the intent home-robot intent-recognition pipeline on Rockchip RK3588 boards.
All-time downloads
23
Public
Repo size
2.4 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.rkllm2.4 GB · 100%
At a glance
- Library
- rkllm
- License
- apache-2.0
- Access
- Public
- Created
- Jul 30, 2026
- Updated
- Jul 31, 2026
- SHA
- 03ce5b30
Model card
From the Hugging Face model README
intent-rk3588-npu
Pre-converted NPU weights for the intent home-robot intent-recognition pipeline on Rockchip RK3588 boards.
| File | Stage | Source model | Format |
|---|---|---|---|
llm/qwen3-1.7b-w8a8-rk3588.rkllm | LLM escalation tier | Qwen/Qwen3-1.7B | RKLLM w8a8, 3 NPU cores |
Converted with rkllm-toolkit 1.3.0 via the repo's scripts/convert_rkllm.py.
Usage (on the board)
bash scripts/download_models.sh llm_rkllm
uv run intent-model --serve --llm-runtime rkllm \
--asr-provider rknn --asr-model-dir models/asr-sensevoice-rknn
Requirements: RKNPU driver >= 0.9.8, librkllmrt.so.
Qwen3-1.7B keeps thinking mode (enable_thinking); ~13 tok/s on RK3588.
Why no GLiNER2 encoder here
Converting the pipeline's GLiNER2 (DeBERTa-v3) encoder to RKNN was attempted
thoroughly (fp16 + int8, graph splitting, every relevant toolkit knob) and is
blocked by rknn-toolkit2 2.3.2 itself: its build phase needs >460 GB RAM at
the model's working sequence length, crashes with integer-overflow mallocs,
and emits artifacts with multi-GB zero-padded sections. On the board the
GLiNER2 encoder runs on CPU via ONNX (--gliner-encoder onnx), which matches
torch accuracy; the NPU's three cores are used by ASR + the LLM.
- Library
- rkllm
- License
- apache-2.0
- Created
- Jul 30, 2026
- Updated
- Jul 31, 2026