litert-community / Phi-4-mini-instruct

huggingface.co
Total runs: 23.2K
24-hour runs: 0
7-day runs: -857
30-day runs: -857
Model's Last Updated: September 23 2025
text-generation

Introduction of Phi-4-mini-instruct

Model Details of Phi-4-mini-instruct

litert-community/Phi-4-mini-instruct

This model provides a few variants of microsoft/Phi-4-mini-instruct that are ready for deployment on Android using the LiteRT 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.

Performance
Android

Note that all benchmark stats are from a Samsung S24 Ultra with 1280 KV cache size, 512 tokens prefill, 128 tokens decode on CPU.

Prefill (tokens/sec) Decode (tokens/sec) Time-to-first-token (sec) Memory (RSS in MB) Model size (MB)

dynamic_int8

80

23

2

6,884

3,940

  • Model Size: measured by the size of the .tflite flatbuffer (serialization format for LiteRT models)
  • Memory: indicator of peak RAM usage
  • The inference is run on CPU is accelerated via the LiteRT XNNPACK delegate with 4 threads
  • Benchmark is done assuming XNNPACK cache is enabled
  • dynamic_int8: quantized model with int8 weights and float activations.

Runs of litert-community Phi-4-mini-instruct on huggingface.co

23.2K
Total runs
0
24-hour runs
-146
3-day runs
-857
7-day runs
-857
30-day runs

More Information About Phi-4-mini-instruct huggingface.co Model

More Phi-4-mini-instruct license Visit here:

https://choosealicense.com/licenses/mit

Phi-4-mini-instruct huggingface.co

Phi-4-mini-instruct huggingface.co is an AI model on huggingface.co that provides Phi-4-mini-instruct's model effect (), which can be used instantly with this litert-community Phi-4-mini-instruct model. huggingface.co supports a free trial of the Phi-4-mini-instruct model, and also provides paid use of the Phi-4-mini-instruct. Support call Phi-4-mini-instruct model through api, including Node.js, Python, http.

litert-community Phi-4-mini-instruct online free

Phi-4-mini-instruct huggingface.co is an online trial and call api platform, which integrates Phi-4-mini-instruct's modeling effects, including api services, and provides a free online trial of Phi-4-mini-instruct, you can try Phi-4-mini-instruct online for free by clicking the link below.

litert-community Phi-4-mini-instruct online free url in huggingface.co:

https://huggingface.co/litert-community/Phi-4-mini-instruct

Phi-4-mini-instruct install

Phi-4-mini-instruct is an open source model from GitHub that offers a free installation service, and any user can find Phi-4-mini-instruct on GitHub to install. At the same time, huggingface.co provides the effect of Phi-4-mini-instruct install, users can directly use Phi-4-mini-instruct installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Phi-4-mini-instruct install url in huggingface.co:

https://huggingface.co/litert-community/Phi-4-mini-instruct

Url of Phi-4-mini-instruct

Provider of Phi-4-mini-instruct huggingface.co

litert-community
ORGANIZATIONS

Other API from litert-community