Instructions to use FastFlowLM/Gemma4-E2B-IT-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FastFlowLM/Gemma4-E2B-IT-NPU2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("FastFlowLM/Gemma4-E2B-IT-NPU2") model = AutoModelForMultimodalLM.from_pretrained("FastFlowLM/Gemma4-E2B-IT-NPU2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download audio_weight.q4nx from FastFlowLM/Gemma4-E2B-IT-NPU2: direct link, hf CLI and curl.
- Browser
- Download file 952 MB
-
https://huggingface.co/FastFlowLM/Gemma4-E2B-IT-NPU2/resolve/main/audio_weight.q4nx
- Command line
-
hf download hf://FastFlowLM/Gemma4-E2B-IT-NPU2/audio_weight.q4nx
-
curl -L -o audio_weight.q4nx https://huggingface.co/FastFlowLM/Gemma4-E2B-IT-NPU2/resolve/main/audio_weight.q4nx
952 MB
- Xet hash:
- 90c4f39e6908591ca9e04a3c425a3b677498226519890caf16441dfa4fd08796
- Size of remote file:
- 952 MB
- SHA256:
- 48d4632ee75ba1fdf40b8369d5961b1edfc86152e51d585aa6bd37b31f6f4895
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.