---
title: Kimi-VL-A3B-Thinking-2506-6bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Kimi-VL-A3B-Thinking-2506-6bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Kimi-VL-A3B-Thinking-2506-6bit.md"
repository: mlx-community/Kimi-VL-A3B-Thinking-2506-6bit
last_updated: 2026-01-28
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - kimi_vl
architectures:
  - KimiVLForConditionalGeneration
base_model:
  - moonshotai/Kimi-VL-A3B-Instruct
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task vlm/text/emb"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 177
stars: 0
tags:
  - mlx
---

# Kimi-VL-A3B-Thinking-2506-6bit

> Kimi-VL-A3B-Thinking-2506-6bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Kimi-VL-A3B-Thinking-2506-6bit This model was converted to MLX format from moonshotai/Kimi-VL-A3B-Thinking-2506 using mlx-vlm version 0.3.2. Refer to the original model card for…

mlx-community/Kimi-VL-A3B-Thinking-2506-6bit 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 mit 许可，基于 moonshotai/Kimi-VL-A3B-Instruct 构建，可用 deploy_task vlm/text/emb、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/Kimi-VL-A3B-Thinking-2506-6bit
- **License**: mit
- **Tasks**: image-text-to-text
- **Base model**: moonshotai/Kimi-VL-A3B-Instruct
- **Inference backends**: deploy_task vlm/text/emb, sglang 0.5.2, vllm 0.9.2
- **Tags**: mlx
- **Downloads**: 177
- **Stars**: 0
- **Last updated**: 2026-01-28

Source: https://www.modelscope.cn/models/mlx-community/Kimi-VL-A3B-Thinking-2506-6bit

---

# mlx-community/Kimi-VL-A3B-Thinking-2506-6bit
This model was converted to MLX format from [`moonshotai/Kimi-VL-A3B-Thinking-2506`]() using mlx-vlm version **0.3.2**.
Refer to the [original model card](https://huggingface.co/moonshotai/Kimi-VL-A3B-Thinking-2506) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model jqlive/Kimi-VL-A3B-Thinking-2506-6bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```