| { |
| "models": [ |
| { |
| "name": "Gemma-3n-E2B-it-int4", |
| "modelId": "google/gemma-3n-E2B-it-litert-preview", |
| "modelFile": "gemma-3n-E2B-it-int4.task", |
| "description": "Preview version of [Gemma 3n E2B](https://ai.google.dev/gemma/docs/gemma-3n) ready for deployment on Android using the [MediaPipe LLM Inference API](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference). The current checkpoint only supports text and vision input, with 4096 context length.", |
| "sizeInBytes": 3136226711, |
| "estimatedPeakMemoryInBytes": 5905580032, |
| "version": "20250520", |
| "llmSupportImage": true, |
| "defaultConfig": { |
| "topK": 64, |
| "topP": 0.95, |
| "temperature": 1.0, |
| "maxTokens": 4096, |
| "accelerators": "cpu,gpu" |
| }, |
| "taskTypes": ["llm_chat", "llm_prompt_lab", "llm_ask_image"] |
| }, |
| { |
| "name": "Gemma-3n-E4B-it-int4", |
| "modelId": "google/gemma-3n-E4B-it-litert-preview", |
| "modelFile": "gemma-3n-E4B-it-int4.task", |
| "description": "Preview version of [Gemma 3n E4B](https://ai.google.dev/gemma/docs/gemma-3n) ready for deployment on Android using the [MediaPipe LLM Inference API](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference). The current checkpoint only supports text and vision input, with 4096 context length.", |
| "sizeInBytes": 4405655031, |
| "estimatedPeakMemoryInBytes": 6979321856, |
| "version": "20250520", |
| "llmSupportImage": true, |
| "defaultConfig": { |
| "topK": 64, |
| "topP": 0.95, |
| "temperature": 1.0, |
| "maxTokens": 4096, |
| "accelerators": "cpu,gpu" |
| }, |
| "taskTypes": ["llm_chat", "llm_prompt_lab", "llm_ask_image"] |
| }, |
| { |
| "name": "Gemma3-1B-IT q4", |
| "modelId": "litert-community/Gemma3-1B-IT", |
| "modelFile": "Gemma3-1B-IT_multi-prefill-seq_q4_ekv2048.task", |
| "description": "A variant of [google/Gemma-3-1B-IT](https://huggingface.co/google/Gemma-3-1B-IT) with 4-bit quantization ready for deployment on Android using the [MediaPipe LLM Inference API](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference)", |
| "sizeInBytes": 554661246, |
| "estimatedPeakMemoryInBytes": 2147483648, |
| "version": "20250514", |
| "defaultConfig": { |
| "topK": 64, |
| "topP": 0.95, |
| "temperature": 1.0, |
| "maxTokens": 1024, |
| "accelerators": "gpu,cpu" |
| }, |
| "taskTypes": ["llm_chat", "llm_prompt_lab"] |
| }, |
| { |
| "name": "Qwen2.5-1.5B-Instruct q8", |
| "modelId": "litert-community/Qwen2.5-1.5B-Instruct", |
| "modelFile": "Qwen2.5-1.5B-Instruct_multi-prefill-seq_q8_ekv1280.task", |
| "description": "A variant of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) with 8-bit quantization ready for deployment on Android using the [MediaPipe LLM Inference API](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference)", |
| "sizeInBytes": 1625493432, |
| "estimatedPeakMemoryInBytes": 2684354560, |
| "version": "20250514", |
| "defaultConfig": { |
| "topK": 40, |
| "topP": 0.95, |
| "temperature": 1.0, |
| "maxTokens": 1024, |
| "accelerators": "cpu" |
| }, |
| "taskTypes": ["llm_chat", "llm_prompt_lab"] |
| }, |
| { |
| "name": "Gemma-4-E2B-it", |
| "modelId": "HawkFranklin-Research/AURA-models", |
| "modelFile": "aura-gemma-4-e2b-it.litertlm", |
| "description": "A LiteRT-LM variant of [Gemma 4 E2B IT](https://huggingface.co/litert-community/gemma-4-E2B-it-litert-lm) saved under an AURA-friendly filename for on-device text generation.", |
| "sizeInBytes": 2588147712, |
| "estimatedPeakMemoryInBytes": 1817370624, |
| "minDeviceMemoryInGb": 8, |
| "commitHash": "main", |
| "url": "https://huggingface.co/HawkFranklin-Research/AURA-models/resolve/main/aura-gemma-4-e2b-it.litertlm?download=true", |
| "defaultConfig": { |
| "topK": 64, |
| "topP": 0.95, |
| "temperature": 1.0, |
| "maxTokens": 4096, |
| "accelerators": "cpu,gpu" |
| }, |
| "taskTypes": ["llm_chat", "llm_prompt_lab"] |
| } |
| ] |
| } |
|
|
