README.md

---
license: other
---

# Qwen3-pruned-6L-from-0.6B-int8-ov
## Description

This is a pruned model, originating from the [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
The model was built to accompany [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) and to be used as a draft model in the context of Speculative Decoding.

The pruning was performed by applying the findings from recent layer-wise pruning research, see [one](https://arxiv.org/abs/2403.17887) of the relevant publications,
followed by the accuracy recovery fine-tuning over synthetic data generated by the target model Qwen/Qwen3-8B.

Qwen3-pruned-6L-from-0.6B-int8-ov is a model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format with weights compressed to int8 by [NNCF](https://github.com/openvinotoolkit/nncf).

## Quantization Parameters

Weight compression was performed using `nncf.compress_weights` with the following parameters:
* mode: **INT8_ASYM**

For more information on quantization, check the [OpenVINO model optimization guide](https://docs.openvino.ai/2024/openvino-workflow/model-optimization-guide/weight-compression.html).

## Compatibility

The provided OpenVINO™ IR model is compatible with:

* OpenVINO version **2025.2** and higher
* Optimum Intel **1.25.3** and higher

## Running Model Inference with OpenVINO GenAI

1. Install packages required for using [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai) with Speculative decoding: 

```bash
pip install -U "openvino-genai>=2025.2.0" huggingface_hub
```

2. Download models from HuggingFace Hub
```python
import huggingface_hub as hf_hub
 
main_model_id = "OpenVINO/Qwen3-8B-int4-ov"
draft_model_id = "OpenVINO/Qwen3-pruned-6L-from-0.6B-int8-ov"
 
main_model_path = "main"
draft_model_path = "draft"
 
hf_hub.snapshot_download(main_model_id, local_dir=main_model_path)
hf_hub.snapshot_download(draft_model_id, local_dir=draft_model_path)
```
3. Run model inference using the speculative decoding and specify the pipeline parameters:
```python
import openvino_genai
 
prompt = "What is OpenVINO?"
 
config = openvino_genai.GenerationConfig()
config.num_assistant_tokens = 3
config.max_new_tokens = 128
 
def streamer(subword):
    print(subword, end='', flush=True)
    return False
 
main_device = "CPU"
draft_device = "CPU"
 
draft_model = openvino_genai.draft_model(draft_model_path, draft_device)
 
scheduler_config = openvino_genai.SchedulerConfig()
scheduler_config.cache_size = 2


pipe = openvino_genai.LLMPipeline(main_model_path, main_device, scheduler_config=scheduler_config, draft_model=draft_model)
 
pipe.generate(prompt, config, streamer)
```

More GenAI usage examples can be found in OpenVINO GenAI library [docs](https://github.com/openvinotoolkit/openvino.genai/blob/master/src/README.md) and [samples](https://github.com/openvinotoolkit/openvino.genai/tree/master/samples)

## Legal Information

The model is distributed under the [Intel Research Use License Agreement](https://huggingface.co/OpenVINO/Qwen3-pruned-6L-from-0.6B-int8-ov/blob/main/LICENSE.md).

The original model is distributed under [Apache License Version 2.0](https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE) license. More details can be found in [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).

## Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See [Intel’s Global Human Rights Principles](https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf). Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.