---
title: Qwen3-1.7B-int4-sym-ov-npu
canonical_url: "https://www.modelscope.cn/models/zhaohb/Qwen3-1.7B-int4-sym-ov-npu"
md_url: "https://www.modelscope.cn/models/zhaohb/Qwen3-1.7B-int4-sym-ov-npu.md"
repository: zhaohb/Qwen3-1.7B-int4-sym-ov-npu
last_updated: 2025-07-03
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
library_name:
  - openvino
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 113
stars: 0
---

# Qwen3-1.7B-int4-sym-ov-npu

> Qwen3-1.7B-int4-sym-ov-npu - zhaohb 在 ModelScope 开源的模型。Description This is Qwen/Qwen3-1.7B model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT4 by NNCF.

zhaohb/Qwen3-1.7B-int4-sym-ov-npu 是 ModelScope 魔搭社区上的text-generation模型，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: zhaohb/Qwen3-1.7B-int4-sym-ov-npu
- **Tasks**: text-generation
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 113
- **Stars**: 0
- **Last updated**: 2025-07-03

Source: https://www.modelscope.cn/models/zhaohb/Qwen3-1.7B-int4-sym-ov-npu

---

### Description
This is Qwen/Qwen3-1.7B model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT4 by NNCF.

### Quantization Parameters
Weight compression was performed using nncf.compress_weights with the following parameters:

mode: INT4_SYM
group_size: -1
ratio: 1.0