---
title: QVQ-72B-Preview-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/QVQ-72B-Preview-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/QVQ-72B-Preview-bf16.md"
repository: mlx-community/QVQ-72B-Preview-bf16
last_updated: 2024-12-25
license: other
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen2_vl
architectures:
  - Qwen2VLForConditionalGeneration
base_model:
  - Qwen/Qwen2-VL-72B
base_model_relation: finetune
parameters: 73.4B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 977
stars: 0
tags:
  - chat
  - mlx
---

# QVQ-72B-Preview-bf16

> QVQ-72B-Preview-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/QVQ-72B-Preview-bf16 This model was converted to MLX format from Qwen/QVQ-72B-Preview using mlx-vlm version 0.1.6. Refer to the original model card for more details on the model. Use with…

mlx-community/QVQ-72B-Preview-bf16 是 ModelScope 魔搭社区上的 73.4B 参数image-text-to-text模型，采用 other 许可，基于 Qwen/Qwen2-VL-72B 构建，可用 deploy_task vlm/text/emb、lmdeploy 0.9.1、sglang 0.5.2 部署。

- **Repository**: mlx-community/QVQ-72B-Preview-bf16
- **License**: other
- **Tasks**: image-text-to-text
- **Parameters**: 73.4B
- **Base model**: Qwen/Qwen2-VL-72B
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: chat, mlx
- **Downloads**: 977
- **Stars**: 0
- **Last updated**: 2024-12-25

Source: https://www.modelscope.cn/models/mlx-community/QVQ-72B-Preview-bf16

---

# mlx-community/QVQ-72B-Preview-bf16
This model was converted to MLX format from [`Qwen/QVQ-72B-Preview`]() using mlx-vlm version **0.1.6**.
Refer to the [original model card](https://huggingface.co/Qwen/QVQ-72B-Preview) for more details on the model.
## Use with mlx

```bash
pip install -U mlx-vlm
```

```bash
python -m mlx_vlm.generate --model mlx-community/QVQ-72B-Preview-bf16 --max-tokens 100 --temp 0.0
```