---
title: P1-VL-30B-A3B-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/P1-VL-30B-A3B-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/P1-VL-30B-A3B-8bit.md"
repository: mlx-community/P1-VL-30B-A3B-8bit
last_updated: 2026-05-19
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_vl_moe
architectures:
  - Qwen3VLMoeForConditionalGeneration
base_model:
  - PRIME-RL/P1-VL-30B-A3B
base_model_relation: quantized
parameters: 9.1B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 10
stars: 0
tags:
  - science
  - physics
  - vision-language
  - reasoning
  - olympiad
  - mlx
---

# P1-VL-30B-A3B-8bit

> P1-VL-30B-A3B-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/P1-VL-30B-A3B-8bit

mlx-community/P1-VL-30B-A3B-8bit 是 ModelScope 魔搭社区上的 9.1B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 PRIME-RL/P1-VL-30B-A3B 构建。

- **Repository**: mlx-community/P1-VL-30B-A3B-8bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 9.1B
- **Base model**: PRIME-RL/P1-VL-30B-A3B
- **Tags**: science, physics, vision-language, reasoning, olympiad, mlx
- **Downloads**: 10
- **Stars**: 0
- **Last updated**: 2026-05-19

Source: https://www.modelscope.cn/models/mlx-community/P1-VL-30B-A3B-8bit

---

# mlx-community/P1-VL-30B-A3B-8bit

This model was converted to MLX format from [`PRIME-RL/P1-VL-30B-A3B`](https://huggingface.co/PRIME-RL/P1-VL-30B-A3B)
using mlx-vlm version **0.4.4**.
Refer to the [original model card](https://huggingface.co/PRIME-RL/P1-VL-30B-A3B) for more details on the model.

## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/P1-VL-30B-A3B-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```