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

This model provides a few variants of

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B that are ready for

deployment on Android using the

LiteRT (fka TFLite) stack,

MediaPipe LLM Inference API and

LiteRt-LM.

Use the models

Colab

*Disclaimer: The target deployment surface for the LiteRT models is

Android/iOS/Web and the stack has been optimized for performance on these

targets. Trying out the system in Colab is an easier way to familiarize yourself

with the LiteRT stack, with the caveat that the performance (memory and latency)

on Colab could be much worse than on a local device.*


Android

Edge Gallery App

• Download or build the app from GitHub.

• Install the app from Google Play

• Follow the instructions in the app.

LLM Inference API

• Download and install

the apk.

• Follow the instructions in the app.

To build the demo app from source, please follow the

instructions

from the GitHub repository.

Performance

Android

Note that all benchmark stats are from a Samsung S24 Ultra with

1280 KV cache size with multiple prefill signatures enabled.

Backend

Quantization

Context Length

Prefill (tokens/sec)

Decode (tokens/sec)

Time-to-first-token (sec)

Model size (MB)

Peak RSS Memory (MB)

GPU Memory (MB)

CPU

dynamic_int8

4096

166.50 tk/s

26.35 tk/s

6.41 s

1831.43 MB

2221 MB

N/A

GPU

dynamic_int8

4096

927.54 tk/s

26.98 tk/s

5.46 s

1831.43 MB

2096 MB

1659 MB

• Model Size: measured by the size of the .tflite flatbuffer (serialization

format for LiteRT models)

• Memory: indicator of peak RAM usage
• The inference on CPU is accelerated via the LiteRT

XNNPACK delegate with 4 threads

• Benchmark is done assuming XNNPACK cache is enabled
• Benchmark is run with cache enabled and initialized. During the first run, the time to first token may differ.
• dynamic_int8: quantized model with int8 weights and float activations.