LiteRT models in the Gemma Family
AI & ML interests
AI for Mobile, Web, and Embedded
Recent Activity
View all activity
Generative AI on device: LLMs, VLMs, audio-LMs (speech LMs), embeddings, and text-to-image — LiteRT / LiteRT-LM ready.
Vision models for LiteRT: image classification, detection, segmentation, keypoints, depth, OCR, enhancement, and zero-shot vision encoders.
LiteRT models that support multi-modality
LiteRT models that can run on Android
LiteRT models that can run on Desktop
Classical Models
Collection for models for Qualcomm hackathon
Collection to host models submitted by community contributors . See contribution guidelines for details.
LiteRT models in the Qwen Family
Automatic Speech Recognition Models
-
litert-community/parakeet-tdt-0.6b-v3
Updated • 8.79k • 15 -
litert-community/parakeet-ctc-0.6b
Automatic Speech Recognition • Updated • 2.36k • 5 -
litert-community/moonshine-tiny
Automatic Speech Recognition • Updated • 4.63k • 4 -
litert-community/Qwen3-ASR-0.6B
Automatic Speech Recognition • Updated • 1.52k • 9
Audio models for LiteRT: speech recognition (ASR), text-to-speech, keyword spotting, and audio codecs.
-
litert-community/parakeet-tdt-0.6b-v3
Updated • 8.79k • 15 -
litert-community/whisper-tiny
Automatic Speech Recognition • Updated • 8.92k • 6 -
litert-community/parakeet-ctc-0.6b
Automatic Speech Recognition • Updated • 2.36k • 5 -
litert-community/whisper-base
Automatic Speech Recognition • Updated • 1.02k • 2
LiteRT image-classification models from litert-community.
LiteRT models that can run on iOS
LiteRT models that can run on the Web
LiteRT Models that can run on Google Tensor
-
litert-community/gemma-4-E2B-it-litert-lm
Updated • 1.26M • 443 -
litert-community/Gemma3-1B-IT
Text Generation • Updated • 12.4k • 913 -
litert-community/embeddinggemma-300m
Sentence Similarity • Updated • 1.8k • 80 -
litert-community/functiongemma-270m-ft-mobile-actions
Text Generation • Updated • 1.12k • 243
Test collection for user profile testing
LiteRT models in the Gemma Family
LiteRT models in the Qwen Family
Generative AI on device: LLMs, VLMs, audio-LMs (speech LMs), embeddings, and text-to-image — LiteRT / LiteRT-LM ready.
Automatic Speech Recognition Models
-
litert-community/parakeet-tdt-0.6b-v3
Updated • 8.79k • 15 -
litert-community/parakeet-ctc-0.6b
Automatic Speech Recognition • Updated • 2.36k • 5 -
litert-community/moonshine-tiny
Automatic Speech Recognition • Updated • 4.63k • 4 -
litert-community/Qwen3-ASR-0.6B
Automatic Speech Recognition • Updated • 1.52k • 9
Vision models for LiteRT: image classification, detection, segmentation, keypoints, depth, OCR, enhancement, and zero-shot vision encoders.
Audio models for LiteRT: speech recognition (ASR), text-to-speech, keyword spotting, and audio codecs.
-
litert-community/parakeet-tdt-0.6b-v3
Updated • 8.79k • 15 -
litert-community/whisper-tiny
Automatic Speech Recognition • Updated • 8.92k • 6 -
litert-community/parakeet-ctc-0.6b
Automatic Speech Recognition • Updated • 2.36k • 5 -
litert-community/whisper-base
Automatic Speech Recognition • Updated • 1.02k • 2
LiteRT models that support multi-modality
LiteRT image-classification models from litert-community.
LiteRT models that can run on Android
LiteRT models that can run on iOS
LiteRT models that can run on Desktop
LiteRT models that can run on the Web
Classical Models
LiteRT Models that can run on Google Tensor
-
litert-community/gemma-4-E2B-it-litert-lm
Updated • 1.26M • 443 -
litert-community/Gemma3-1B-IT
Text Generation • Updated • 12.4k • 913 -
litert-community/embeddinggemma-300m
Sentence Similarity • Updated • 1.8k • 80 -
litert-community/functiongemma-270m-ft-mobile-actions
Text Generation • Updated • 1.12k • 243
Collection for models for Qualcomm hackathon
Collection to host models submitted by community contributors . See contribution guidelines for details.
Test collection for user profile testing