---
title: Qwen3-8B-Instruct
canonical_url: "https://www.modelscope.cn/models/JunHowie/Qwen3-8B-Instruct"
md_url: "https://www.modelscope.cn/models/JunHowie/Qwen3-8B-Instruct.md"
repository: JunHowie/Qwen3-8B-Instruct
chinese_name: Qwen3-8B-Instruct
last_updated: 2025-11-25
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
base_model:
  - Qwen/Qwen3-8B
base_model_relation: finetune
parameters: 8.2B
tensor_type:
  - BF16
library_name:
  - safetensors
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 3350
stars: 15
---

# Qwen3-8B-Instruct

> Qwen3-8B-Instruct - JunHowie 在 ModelScope 开源的模型。NOTE：This model is the Instruct-aligned variant, and it will not generate blocks in its outputs. Additionally, there is no need to specify enablethinking=False anymore.

JunHowie/Qwen3-8B-Instruct 是 ModelScope 魔搭社区上的 8.2B 参数text-generation模型，采用 apache-2.0 许可，基于 Qwen/Qwen3-8B 构建，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: JunHowie/Qwen3-8B-Instruct
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 8.2B
- **Base model**: Qwen/Qwen3-8B
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 3350
- **Stars**: 15
- **Last updated**: 2025-11-25

Source: https://www.modelscope.cn/models/JunHowie/Qwen3-8B-Instruct

---

# Qwen3-8B-Instruct

**NOTE：This model is the Instruct-aligned variant, and it will not generate ``<think></think>``  blocks in its outputs.
Additionally, there is no need to specify enable_thinking=False anymore.**




This model was trained using ms-swift as the post-training framework, with full-parameter SFT on 4 × 80GB GPUs.<br>
The dataset used is the Chinese Distillation Dataset based on Qwen3-235B-2507
<br>available at:
https://www.modelscope.cn/datasets/swift/Chinese-Qwen3-235B-2507-Distill-data-110k-SFT


### 【vLLM Startup Command】
```
vllm serve JunHowie/Qwen3-8B-Instruct 
```

### 【Dependencies】
```
vllm>=0.10.2
transformers>=4.56.1
```

### 【Model Download】

```python
from modelscope import snapshot_download
snapshot_download('JunHowie/Qwen3-8B-Instruct', cache_dir="your_local_path")
```