---
title: Qwen3-1.7B-W4A8-V1
canonical_url: "https://www.modelscope.cn/models/vllm-ascend/Qwen3-1.7B-W4A8-V1"
md_url: "https://www.modelscope.cn/models/vllm-ascend/Qwen3-1.7B-W4A8-V1.md"
repository: vllm-ascend/Qwen3-1.7B-W4A8-V1
chinese_name: Qwen3-1.7B-W4A8-V1
last_updated: 2025-10-09
license: "Apache License 2.0"
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
base_model:
  - Qwen/Qwen3-1.7B
base_model_relation: quantized
parameters: 1.5B
tensor_type:
  - F32
  - BF16
  - F16
  - I8
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 4900
stars: 2
---

# Qwen3-1.7B-W4A8-V1

> Qwen3-1.7B-W4A8-V1 - vllm-ascend 在 ModelScope 开源的模型。Qwen3-1.7B-W4A8-V1 此模型使用msmodelslim 对 Qwen3 1.7B 进行 w4a8 dynamic 量化（新版格式） 量化准备

vllm-ascend/Qwen3-1.7B-W4A8-V1 是 ModelScope 魔搭社区上的 1.5B 参数text-generation模型，采用 Apache License 2.0 许可，基于 Qwen/Qwen3-1.7B 构建，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: vllm-ascend/Qwen3-1.7B-W4A8-V1
- **License**: Apache License 2.0
- **Tasks**: text-generation
- **Parameters**: 1.5B
- **Base model**: Qwen/Qwen3-1.7B
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 4900
- **Stars**: 2
- **Last updated**: 2025-10-09

Source: https://www.modelscope.cn/models/vllm-ascend/Qwen3-1.7B-W4A8-V1

---

# Qwen3-1.7B-W4A8-V1
此模型使用msmodelslim 对 Qwen3 1.7B 进行 w4a8 dynamic 量化（新版格式）
## 量化准备
```bash
git clone https://gitcode.com/ascend/msit

cd msit/msmodelslim
bash install.sh
pip install accelerate

cd msmodelslim/example/Qwen
```
## 量化方法
```bash
# Original weight path, Replace with your local model path
MODEL_PATH=/path/to/model
# Path to save converted weight, Replace with your local path
SAVE_PATH=/path/to/save/quantmodel
python quant_qwen.py \
          --model_path $MODEL_PATH \
          --save_directory $SAVE_PATH \
          --device_type npu \
          --model_type qwen3 \
          --calib_file None \
          --anti_method m6 \
          --anti_calib_file ./calib_data/mix_dataset.json \
          --w_bit 4 \
          --a_bit 8 \
          --is_lowbit True \
          --open_outlier False \
          --group_size 128 \
          --is_dynamic True \
          --trust_remote_code True \
          --w_method HQQ

```

## 使用方法

1. 在vllm-ascend中推理
```bash
export VLLM_USE_MODELSCOPE=True
vllm serve vllm-ascend/Qwen3-1.7B-W4A8-V1 --gpu-memory-utilization 0.96 --quantization ascend --max-model-len 9600 

```

#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('vllm-ascend/Qwen3-1.7B-W4A8-V1')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/Anionex/Qwen3-1.7B-W4A8-V1.git
```
