DeepSeek-R1-Distill-Qwen-1.5B Open-Source Model - Multi-variant Adaptation for Multiple Platforms, Effortless Deployment on Android Systems

Deepseek R1 Distill Qwen 1.5B

Developed by litert-community

Multiple variants based on DeepSeek-R1-Distill-Qwen-1.5B, adapted for LiteRT framework and MediaPipe LLM inference API, deployable on Android platforms.

Large Language Model Open Source License:MIT #Mobile Optimization #Low Memory Consumption #Dynamic Quantization

Downloads 138

Release Time : 2/14/2025

Model Overview

This model provides multiple variants of DeepSeek-R1-Distill-Qwen-1.5B, which have been adapted for the LiteRT framework and MediaPipe LLM inference API, making them deployable on Android platforms.

Model Features

Adapted for LiteRT Framework

The model has been adapted for the LiteRT framework, enabling deployment on Android platforms.

Supports MediaPipe LLM Inference API

The model supports the MediaPipe LLM inference API, facilitating usage on mobile devices.

High-Performance Inference

Delivers outstanding performance on Android devices, supporting dynamic int8 quantization to significantly boost inference speed.

Model Capabilities

Text Generation

Chat

Use Cases

Mobile Applications

Android Chat Application

Deploy a chatbot application on Android devices.

Supports high-concurrency text generation and rapid responses.

Property	Backend	Prefill (tokens/sec)	Decode (tokens/sec)	Time-to-first-token (sec)	Memory (RSS in MB)	Model size (MB)
fp32 (baseline)	cpu	39.56 tk/s	1.43 tk/s	19.24 s	5,997 MB	6,794 MB
dynamic_int8	cpu	110.58 tk/s	12.96 tk/s	6.81 s	3,598 MB	1,774 MB

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Deepseek R1 Distill Qwen 1.5B

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 litert-community/DeepSeek-R1-Distill-Qwen-1.5B

🚀 Quick Start

Use the models

Colab

Android

📊 Performance

Android

📄 License