---
title: Molmo-7B-D-0924-6bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Molmo-7B-D-0924-6bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Molmo-7B-D-0924-6bit.md"
repository: mlx-community/Molmo-7B-D-0924-6bit
last_updated: 2025-02-06
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - molmo
architectures:
  - MolmoForCausalLM
base_model:
  - openai/clip-vit-large-patch14-336
  - Qwen/Qwen2-7B
base_model_relation: finetune
parameters: 2.2B
tensor_type:
  - F16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task vlm/text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "vllm 0.9.2"
downloads: 1015
stars: 0
tags:
  - multimodal
  - olmo
  - molmo
  - pixmo
  - mlx
---

# Molmo-7B-D-0924-6bit

> Molmo-7B-D-0924-6bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Molmo-7B-D-0924-6bit This model was converted to MLX format from allenai/Molmo-7B-D-0924 using mlx-vlm version 0.1.7. Refer to the original model card for more details on the model. Use…

mlx-community/Molmo-7B-D-0924-6bit 是 ModelScope 魔搭社区上的 2.2B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 openai/clip-vit-large-patch14-336、Qwen/Qwen2-7B 构建，可用 deploy_task vlm/text/emb、lmdeploy_turbomind 0.9.1、vllm 0.9.2 部署。

- **Repository**: mlx-community/Molmo-7B-D-0924-6bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 2.2B
- **Base model**: openai/clip-vit-large-patch14-336, Qwen/Qwen2-7B
- **Inference backends**: deploy_task vlm/text/emb, lmdeploy_turbomind 0.9.1, vllm 0.9.2
- **Tags**: multimodal, olmo, molmo, pixmo, mlx
- **Downloads**: 1015
- **Stars**: 0
- **Last updated**: 2025-02-06

Source: https://www.modelscope.cn/models/mlx-community/Molmo-7B-D-0924-6bit

---

# mlx-community/Molmo-7B-D-0924-6bit
This model was converted to MLX format from [`allenai/Molmo-7B-D-0924`]() using mlx-vlm version **0.1.7**.
Refer to the [original model card](https://huggingface.co/allenai/Molmo-7B-D-0924) for more details on the model.
## Use with mlx

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

```bash
python -m mlx_vlm.generate --model mlx-community/Molmo-7B-D-0924-6bit --max-tokens 100 --temp 0.0
```