Downloads · 30 days
113
19% of all-time downloads
Qwen3-4B-Instruct-2507_w8a8_g128_1.2.2_rkllm
flylcw/Qwen3-4B-Instruct-2507_w8a8_g128_1.2.2_rkllm
Qwen3-4B-Instruct-2507_w8a8_g128_1.2.2_rkllm is a text generation model from flylcw. Use it when you need the model to write or continue text. It is set up for rkllm. The card lists the license as apache-2.0.
My quant for Rock5B (RK3588 board) Author: @flylcw 建议运行环境：RKLLM-Toolkit在1.2.x应该都可运行，NPU驱动版本需v0.9.8
All-time downloads
598
Public
Repo size
4.8 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.rkllm4.8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- rkllm
- License
- apache-2.0
- Access
- Public
- Created
- Nov 5, 2025
- Updated
- Nov 9, 2025
- SHA
- 21aac034
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-4B-Instruct-2507_w8a8_g128
- My quant for Rock5B (RK3588 board)
- Author: @flylcw
- 建议运行环境：RKLLM-Toolkit在1.2.x应该都可运行，NPU驱动版本需>v0.9.8
Conversion details:
- RKLLM-Toolkit version: v1.2.2
- NPU driver: v0.9.8
- Python: 3.11
- Quantization: w8a8_g128
- Output: single-file .rkllm artifact
- Modifications: quantization (w8a8_g128), export to .rkllm format for RK3588 SBCs
- Task
- Text Generation
- Library
- rkllm
- License
- apache-2.0
- Languages
- en, zh
- Created
- Nov 5, 2025
- Updated
- Nov 9, 2025