metadata
license: mit
tags:
- LiteRT
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
litert-community/DeepSeek-R1-Distill-Qwen-1.5B
This model was converted to LiteRT (aka TFLite) format from deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B using Google AI Edge Torch.
Run the model in colab
Run the model on Android
Please follow the instructions.
Benchmarking results
Note that all benchmark stats are from a Samsung S24 Ultra.
| Model | Params | GGML tk/s (CPU, 4 threads) | GGML tk/s (CPU, 8 threads) | LiteRT tk/s (XNNPACK, 4 threads) | LiteRT tk/s (XNNPACK, 8 threads) | |
|---|---|---|---|---|---|---|
| DeepSeek-R1-Distill-Qwen-1.5B (Int8 quantized) | 1.78 B | Prefill 512 tokens | 64.66 | 87.18 | 260.95 | 299.15 |
| Decode 128 tokens | 23.85 | 15.37 | 23.126 | 10.486 |