LiteRT Community

LiteRT is Google's on-device framework for high-performance ML & GenAI deployment on edge platforms. It is the improved successor to TensorFlow Lite. On this community page, you can find ready-to-run LiteRT models for a wide range of ML/AI tasks.

Within this ecosystem, LiteRT-LM specializes in cutting edge GenAI. Recognizing that LLMs now function as complex pipelines of related models rather than single standalone models, LiteRT-LM leverages LiteRT to deliver an optimized solution for running LLMs on-device.

Both LiteRT and LiteRT-LM can run on a variety of devices including Android, iOS, Windows, macOS, Linux, IoT and Web allow easy deployment and scaling across a diverse device landscape.

Trying it Live

Not sure where to start? We recommend first trying our models in our Google AI Edge Gallery app on Android and iOS.

🌟 Community's Picks of the Week

• EmbeddingGemma v2 (Embedding): embeddinggemma-2-740m-litert-lm (EmbeddingGemma 2 740M is the full, natively multimodal variant of the EmbeddingGemma 2 family). embeddinggemma-2-text-vision-440m-litert-lm (EmbeddingGemma 2 Text Vision 440M is a lightweight, multimodal (text and vision) variant). embeddinggemma-2-text-270m-litert-lm (EmbeddingGemma 2 Text 270M is a highly efficient, text-only variant). They are optimized for low-latency deployment on consumer hardware and edge devices via LiteRT. Main Model Card: google/embeddinggemma-2.
• Idol (Image-to-3D) speridlabs' Idol (with the idol-turbo LoRA), a model that turns one photo of an object into a 3D Gaussian splat, as LiteRT graphs with its pipeline in Python and a Kotlin sample app; the DINOv3 image encoder is in a separate, gated repo.
• Qwen3.5-4B-3D-Coder (Text Generation) CCORE's Qwen3.5-4B-3D-Coder, a fine-tune of Qwen3.5-4B that turns a scene description into one self-contained HTML file with an interactive Three.js 3D scene, as two LiteRT-LM files (text only, thinking off) with a 16,384- or 32,768-token KV cache.
• Unlimited-OCR-2 (Image-Text-to-Text) Baidu's Unlimited-OCR-2, a document-parsing model that writes a page as labeled blocks with boxes (tables in HTML, formulas in LaTeX), as one 3.81 GB LiteRT-LM file that reads one page per request.
• LFM3-Omni-2B-LiteRT (Any-to-Any) Liquid AI's LFM3-Omni-2B, which reads text, pictures and audio and answers in text, as one 3.23 GB LiteRT-LM file, with LiteRT graphs and a Python runner for speech output.
• Audio8-TTS-Realistic-0.6b (Text-to-Speech) Edge0's Audio8-TTS-Realistic-Air (formerly Audio8-TTS-Realistic-0.6b), a 23-language text-to-speech model that can clone a voice from a recording and its transcript, as five LiteRT graphs with a Python host loop and a Kotlin sample app.
• NVIDIA-NemotronLabs-RE-USE-LiteRT (Audio-to-Audio) NVIDIA's NemotronLabs RE-USE, one speech-enhancement network for noisy, reverberant, clipped, band-limited or codec-damaged speech, as two LiteRT graphs that restore 2 s of 16 kHz audio per run, with the host code (STFT and chunking) in Python and Kotlin.

Community Contributions

Are we missing your favorite model? You can convert and run PyTorch, TensorFlow, or JAX models to the classic TFLite format using the LiteRT conversion and optimization tools. Or for LLMs, you can use the LiteRT Torch Generative API. When your model is ready, join the LiteRT community org and upload the model here for others to try!

Submission Guidelines

• Model Conversion: Your model must be converted using the LiteRT-Torch or Generative API in .tflite or .litertlm formats.
• Location: All contributions must be made in the community contribution folder (e.g., LiteRT-Community/community-contribution/mobile-bert).
• Licensing: If your model has a license, it must be either an Apache 2.0 or MIT open-source license. Models with no license are also accepted.
• Data Provenance and Privacy: If applicable, you must include a summary of the model's training data in your submission. Additionally, you must provide confirmation that all Personally Identifiable Information (PII) has been scrubbed from the data.

Policies & Support

• Content Policy: All uploaded models must fully comply with the Hugging Face content guidelines.
• Community Moderation: The Google AI Edge team will not actively moderate community contributions to this community, except for reactive removal in clear cases of spam or abuse.
• Conversion Requests: In the event that you cannot successfully convert a .tflite or .litertlm model, you may submit a PR requesting conversion support from the LiteRT team.