Downloads · 30 days
18
8% of all-time downloads
RK182X-LLM-Qwen2.5-3B-Instruct
RKNNAI/RK182X-LLM-Qwen2.5-3B-Instruct
RK182X-LLM-Qwen2.5-3B-Instruct is a text generation model from RKNNAI. Use it when you need the model to write or continue text. The card lists the license as other.
All-time downloads
212
Public
Repo size
2.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.weight1.9 GB · 75%
At a glance
- Task
- Text Generation
- License
- other
- Access
- Public
- Created
- Sep 24, 2026
- Updated
- Sep 28, 2026
- SHA
- 41bee770
Try a prompt
Base models
Model card
From the Hugging Face model README
RK182X-LLM-Qwen2.5-3B-Instruct
1. Model Overview
This repository provides an RKNN LLM model converted from Qwen/Qwen2.5-3B-Instruct.
- Model ID:
RKNNAI/RK182X-LLM-Qwen2.5-3B-Instruct - Model Display Name:
RK182X-LLM-Qwen2.5-3B-Instruct - RKNN Runtime Version:
v1.1.0 - Source Model:
Qwen/Qwen2.5-3B-Instruct - Model Type: LLM
- Chip Label: RK182X
- Supported Chips: RK1820, RK1828
Available Models
| RKNN Runtime Version | Configuration Directory | Supported Chips | Quantization | NPU Cores | Context Length (tokens) | KVCache |
|---|---|---|---|---|---|---|
v1.1.0 | Qwen2.5-3B-Instruct-w4a16-8-2048 | RK1820, RK1828 | w4a16 | 8 | 2048 (2k) | fp16 |
2. Files
| File or Directory | Description |
|---|---|
LICENSE | Source model license |
Notice | License, usage requirements, and attribution |
<configuration-directory>/ | Matching model files |
Subdirectory README.md | Configuration documentation (English) |
Subdirectory README_CN.md | Configuration documentation (Chinese) |
Subdirectory config.json | Model configuration and file manifest |
Subdirectory SHA256SUMS | SHA-256 checksums of the files in this directory (excluding this file) |
3. Download
Download the full repository from ModelScope:
modelscope download --model RKNNAI/RK182X-LLM-Qwen2.5-3B-Instruct --revision v1.1.0 --local_dir ./RK182X-LLM-Qwen2.5-3B-Instruct
Download the full repository from Hugging Face:
hf download RKNNAI/RK182X-LLM-Qwen2.5-3B-Instruct --revision v1.1.0 --local-dir ./RK182X-LLM-Qwen2.5-3B-Instruct
Download a specific configuration from ModelScope:
from modelscope import snapshot_download
snapshot_download(
"RKNNAI/RK182X-LLM-Qwen2.5-3B-Instruct",
revision="v1.1.0",
allow_patterns=["README.md", "README_CN.md", "LICENSE", "Notice", "Qwen2.5-3B-Instruct-w4a16-8-2048/**"],
local_dir="./RK182X-LLM-Qwen2.5-3B-Instruct",
)
Download a specific configuration from Hugging Face:
hf download RKNNAI/RK182X-LLM-Qwen2.5-3B-Instruct --revision v1.1.0 --include "README.md" "README_CN.md" "LICENSE" "Notice" "Qwen2.5-3B-Instruct-w4a16-8-2048/**" --local-dir ./RK182X-LLM-Qwen2.5-3B-Instruct
4. SHA-256 Verification
Run in the configuration directory:
cd ./RK182X-LLM-Qwen2.5-3B-Instruct/Qwen2.5-3B-Instruct-w4a16-8-2048
sha256sum -c SHA256SUMS
Deploy only after all entries show OK.
5. Compatibility and Limitations
- Supported Chips: RK1820, RK1828.
- Use the matching RKNN Runtime and driver. Check the device-side version with
rknn-smi -vbefore running. - Use the files from the selected configuration directory together.
6. Copyright and License
See LICENSE in the repository root for the source model license; The RKNN Toolkit and RKNN Runtime license terms also apply.
This release is an RKNN-converted/quantized derivative of the source model. The original license and attribution notices are retained; see Notice.
The source model uses Qwen RESEARCH LICENSE AGREEMENT, not Apache 2.0.
Built with Qwen.
- Task
- Text Generation
- License
- other
- Created
- Sep 24, 2026
- Updated
- Sep 28, 2026