---
title: Qwopus3.5-9B-v3-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Qwopus3.5-9B-v3-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Qwopus3.5-9B-v3-4bit.md"
repository: mlx-community/Qwopus3.5-9B-v3-4bit
last_updated: 2026-04-05
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
base_model:
  - Jackrong/Qwopus3.5-9B-v3
base_model_relation: adapter
parameters: 1.9B
tensor_type:
  - BF16
  - U32
  - F32
library_name:
  - lora
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
  - ko
downloads: 139
stars: 0
tags:
  - unsloth
  - qwen
  - qwen3.5
  - reasoning
  - chain-of-thought
  - lora
  - competitive-programming
  - mlx
---

# Qwopus3.5-9B-v3-4bit

> Qwopus3.5-9B-v3-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Qwopus3.5-9B-v3-4bit

mlx-community/Qwopus3.5-9B-v3-4bit 是 ModelScope 魔搭社区上的 1.9B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 Jackrong/Qwopus3.5-9B-v3 构建。

- **Repository**: mlx-community/Qwopus3.5-9B-v3-4bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 1.9B
- **Base model**: Jackrong/Qwopus3.5-9B-v3
- **Tags**: unsloth, qwen, qwen3.5, reasoning, chain-of-thought, lora, competitive-programming, mlx
- **Downloads**: 139
- **Stars**: 0
- **Last updated**: 2026-04-05

Source: https://www.modelscope.cn/models/mlx-community/Qwopus3.5-9B-v3-4bit

---

# mlx-community/Qwopus3.5-9B-v3-4bit

This model was converted to MLX format from [`Jackrong/Qwopus3.5-9B-v3`](https://huggingface.co/Jackrong/Qwopus3.5-9B-v3)
using mlx-vlm version **0.4.4**.
Refer to the [original model card](https://huggingface.co/Jackrong/Qwopus3.5-9B-v3) for more details on the model.

## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/Qwopus3.5-9B-v3-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```