Instructions to use PeppX/gemma-4-e2b-uncensored-litertlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use PeppX/gemma-4-e2b-uncensored-litertlm with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=PeppX/gemma-4-e2b-uncensored-litertlm \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
Any chance for a Pixel 10 Pro (Tensor G5) version so I can use TPU?
#2
by Kalemnor - opened
I've seen you compiled it for Tensor G4, could you make a version for Tensor G5. So Google backend and Tensor G5 soc?
try it once on jegly/box app - this repo got 2 models .safetensors maybe it works - but your best bet is still gpu. and if you got Pixel 10 Pro, I highly recommend typomonster/supergemma4-e4b-abliterated-litert-lm ; your pixel 10 pro is more than just capable of running it, I use the same on my other device and supergemma4-26b-a4b/31b-gguf on my PC.
PeppX changed discussion status to closed
PeppX changed discussion status to open
PeppX changed discussion status to closed
PeppX changed discussion status to open