Instructions to use OpenFlowLM/Gemma3-4B-Text-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenFlowLM/Gemma3-4B-Text-NPU2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenFlowLM/Gemma3-4B-Text-NPU2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download dequant.xclbin from OpenFlowLM/Gemma3-4B-Text-NPU2: direct link, hf CLI and curl.
- Browser
- Download file 115 kB
-
https://huggingface.co/OpenFlowLM/Gemma3-4B-Text-NPU2/resolve/main/dequant.xclbin
- Command line
-
hf download hf://OpenFlowLM/Gemma3-4B-Text-NPU2/dequant.xclbin
-
curl -L -o dequant.xclbin https://huggingface.co/OpenFlowLM/Gemma3-4B-Text-NPU2/resolve/main/dequant.xclbin
115 kB
- Xet hash:
- 27a4fa64079b396375df8298a2073c02fa692e83af2c3483467ccb3ab53a3ef0
- Size of remote file:
- 115 kB
- SHA256:
- a1be8893482f4d6f3634621e9f1c52355ce082cb768300ead02a54b05026b74c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.