Instructions to use litert-community/Qwen2.5-1.5B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use litert-community/Qwen2.5-1.5B-Instruct 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 litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=litert-community/Qwen2.5-1.5B-Instruct \ model.litertlm \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
Qwen3 4B in the plan?
Will you add Qwen3 4B, or models like LLaMA 3 8B / 3B?
Thank you.
We have plans to support several of the Qwen 3 models soon but the exact sizes are TBD.
Unfortunately, we will not be able to post the LLaMA 3 8B / 3B models here for licensing reasons. Advanced users could export those models themselves via the Generative API (https://github.com/google-ai-edge/ai-edge-torch).
but not with GPU support 😥
It looks like the documentation is out-of-date. The AI Edge Torch Generative API can support GPU. In fact, most non-Gemma models in the litert-community were exported with GPU support via this API.
I have informed the documentation owners that their page needs to be updated to reflect the latest behavior of the code.