litert-community / Qwen3-4B

huggingface.co
Total runs: 6.3K
24-hour runs: 0
7-day runs: -118
30-day runs: -1.5K
Model's Last Updated: June 05 2026
text-generation

Introduction of Qwen3-4B

Model Details of Qwen3-4B

Qwen3-4B LiteRT Model

This repository contains a LiteRT-LM version of the Qwen3-4B model, specifically optimized for on-device text generation.

Key Features
  • Quantization: Weights are quantized by torchao to INT8 (channel-wise), and the KV cache is kept in Float32 to balance performance and accuracy.
  • Optimized for Mobile: Designed for efficient execution on mobile and edge devices via LiteRT.
  • Multilingual Support: Inherits strong multilingual capabilities from the base Qwen3-4B model.
Compatiblity

Tested on macOS, Linux CPU/GPU and Android CPU.

Model Metadata
  • Filename: qwen3_4b_channelwise_int8_float32kv.litertlm
  • Model Size: 5.28 GB
  • Quantization Mode: Channel-wise INT8 (Weights), Float32 (KV Cache)
Try it

Install uv and run

uv tool install litert-lm
uvx litert-lm run --from-huggingface-repo=litert-community/Qwen3-4B qwen3_4b_channelwise_int8_float32kv.litertlm  --prompt="What is the capital of France?"
Integration

Ready to integrate this into your product? Get started here .

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen3,
    title  = {Qwen3},
    url    = {https://qwenlm.github.io/blog/qwen3/},
    author = {Qwen Team},
    month  = {April},
    year   = {2025}
}

Runs of litert-community Qwen3-4B on huggingface.co

6.3K
Total runs
0
24-hour runs
41
3-day runs
-118
7-day runs
-1.5K
30-day runs

More Information About Qwen3-4B huggingface.co Model

More Qwen3-4B license Visit here:

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

Qwen3-4B huggingface.co

Qwen3-4B huggingface.co is an AI model on huggingface.co that provides Qwen3-4B's model effect (), which can be used instantly with this litert-community Qwen3-4B model. huggingface.co supports a free trial of the Qwen3-4B model, and also provides paid use of the Qwen3-4B. Support call Qwen3-4B model through api, including Node.js, Python, http.

litert-community Qwen3-4B online free

Qwen3-4B huggingface.co is an online trial and call api platform, which integrates Qwen3-4B's modeling effects, including api services, and provides a free online trial of Qwen3-4B, you can try Qwen3-4B online for free by clicking the link below.

litert-community Qwen3-4B online free url in huggingface.co:

https://huggingface.co/litert-community/Qwen3-4B

Qwen3-4B install

Qwen3-4B is an open source model from GitHub that offers a free installation service, and any user can find Qwen3-4B on GitHub to install. At the same time, huggingface.co provides the effect of Qwen3-4B install, users can directly use Qwen3-4B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Qwen3-4B install url in huggingface.co:

https://huggingface.co/litert-community/Qwen3-4B

Url of Qwen3-4B

Provider of Qwen3-4B huggingface.co

litert-community
ORGANIZATIONS

Other API from litert-community