litert-community / Qwen2.5-1.5B-Instruct

huggingface.co
Total runs: 82.5K
24-hour runs: 0
7-day runs: 8.2K
30-day runs: 10.8K
Model's Last Updated: November 26 2025
text-generation

Introduction of Qwen2.5-1.5B-Instruct

Model Details of Qwen2.5-1.5B-Instruct

litert-community/Qwen2.5-1.5B-Instruct

This model provides a few variants of Qwen/Qwen2.5-1.5B-Instruct that are ready for deployment on Android using the LiteRT (fka TFLite) stack and MediaPipe LLM Inference API .

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.

Open In Colab

Android
  • 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.

iOS
  • Clone the MediaPipe samples repository and follow the instructions to build the LLM Inference iOS Sample App using XCode.
  • Run the app via the iOS simulator or deploy to an iOS device.
Performance
Android

Note that all benchmark stats are from a Samsung S24 Ultra and multiple prefill signatures enabled.

Backend Quantization scheme Context length Prefill (tokens/sec) Decode (tokens/sec) Time-to-first-token (sec) CPU Memory (RSS in MB) GPU Memory (RSS in MB) Model size (MB)

CPU

fp32 (baseline)

1280

27 tk/s

6 tk/s

9.88 s

6,144 MB

5,895 MB

🔗

dynamic_int8

1280

106 tk/s

23 tk/s

2.74 s

1,820 MB

1,523 MB

🔗

4096

63 tk/s

20 tk/s

4.40 s

2,042 MB

1,523 MB

🔗

GPU

1280

706 tk/s

24 tk/s

6.94 s

3,175 MB

1,504 MB

1,523 MB

🔗

4096

417 tk/s

22 tk/s

7.93 s

3,176 MB

1,875 MB

1,523 MB

🔗

  • For the list of supported quantization schemes see supported-schemes . For these models, we are using prefill signature lengths of 32, 128, 512 and 1280.
  • 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 run with cache enabled and initialized. During the first run, the time to first token may differ.

Runs of litert-community Qwen2.5-1.5B-Instruct on huggingface.co

82.5K
Total runs
0
24-hour runs
2.8K
3-day runs
8.2K
7-day runs
10.8K
30-day runs

More Information About Qwen2.5-1.5B-Instruct huggingface.co Model

More Qwen2.5-1.5B-Instruct license Visit here:

https://choosealicense.com/licenses/apache-2.0

Qwen2.5-1.5B-Instruct huggingface.co

Qwen2.5-1.5B-Instruct huggingface.co is an AI model on huggingface.co that provides Qwen2.5-1.5B-Instruct's model effect (), which can be used instantly with this litert-community Qwen2.5-1.5B-Instruct model. huggingface.co supports a free trial of the Qwen2.5-1.5B-Instruct model, and also provides paid use of the Qwen2.5-1.5B-Instruct. Support call Qwen2.5-1.5B-Instruct model through api, including Node.js, Python, http.

litert-community Qwen2.5-1.5B-Instruct online free

Qwen2.5-1.5B-Instruct huggingface.co is an online trial and call api platform, which integrates Qwen2.5-1.5B-Instruct's modeling effects, including api services, and provides a free online trial of Qwen2.5-1.5B-Instruct, you can try Qwen2.5-1.5B-Instruct online for free by clicking the link below.

litert-community Qwen2.5-1.5B-Instruct online free url in huggingface.co:

https://huggingface.co/litert-community/Qwen2.5-1.5B-Instruct

Qwen2.5-1.5B-Instruct install

Qwen2.5-1.5B-Instruct is an open source model from GitHub that offers a free installation service, and any user can find Qwen2.5-1.5B-Instruct on GitHub to install. At the same time, huggingface.co provides the effect of Qwen2.5-1.5B-Instruct install, users can directly use Qwen2.5-1.5B-Instruct installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Qwen2.5-1.5B-Instruct install url in huggingface.co:

https://huggingface.co/litert-community/Qwen2.5-1.5B-Instruct

Url of Qwen2.5-1.5B-Instruct

Provider of Qwen2.5-1.5B-Instruct huggingface.co

litert-community
ORGANIZATIONS

Other API from litert-community