---
title: DeepSeek-V4-Flash-Vision-Exp-MLX
canonical_url: "https://www.modelscope.ai/models/inferencerlabs/DeepSeek-V4-Flash-Vision-Exp-MLX"
md_url: "https://www.modelscope.ai/models/inferencerlabs/DeepSeek-V4-Flash-Vision-Exp-MLX.md"
repository: inferencerlabs/DeepSeek-V4-Flash-Vision-Exp-MLX
last_updated: 2026-09-04
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - deepseek_v4
architectures:
  - DeepseekV4ForCausalLM
base_model:
  - deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
base_model_relation: finetune
parameters: 46.9B
tensor_type:
  - BF16
  - F32
  - I32
  - U32
  - U8
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 75
stars: 0
tags:
  - mlx
---

# DeepSeek-V4-Flash-Vision-Exp-MLX

> DeepSeek-V4-Flash-Vision-Exp-MLX - An open-source model by inferencerlabs on ModelScope. DeepSeek-V4-Flash-Vision-Exp

inferencerlabs/DeepSeek-V4-Flash-Vision-Exp-MLX is a 46.9B-parameter image-text-to-text model on ModelScope. derived from deepseek-ai/DeepSeek-V4-Flash-Vision-Exp.

- **Repository**: inferencerlabs/DeepSeek-V4-Flash-Vision-Exp-MLX
- **Tasks**: image-text-to-text
- **Parameters**: 46.9B
- **Base model**: deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
- **Tags**: mlx
- **Downloads**: 75
- **Stars**: 0
- **Last updated**: 2026-09-04

Source: https://www.modelscope.ai/models/inferencerlabs/DeepSeek-V4-Flash-Vision-Exp-MLX

---

# DeepSeek-V4-Flash-Vision-Exp

See DeepSeek-V4-Flash-Vision-Exp in action: [demonstration videos](https://youtube.com/xcreate)
   
For improved performance, download and enable a compatible [MTP speculative decoder](https://huggingface.co/models?search=inferencerlabs/deepseek-v4-flash-vision-exp-mtp-mlx).

#### Tested with [Inferencer app v2.3.7](https://inferencer.com)
- M3 Ultra: ~31 tokens/s @ 1000 tokens ~146.4 GiB

<p style="margin-bottom:0px;">
<strong>The quantized weights of the base model were repacked for a lossless conversion.</strong>
</p>

![Screenshot 1](https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/P2dkNXrjAYL2bbr0aSf8r.jpeg)

![Screenshot 2](https://cdn-uploads.huggingface.co/production/uploads/688479d616f1ec82fa645019/5fMhqUZtroMKpzbiQHA8U.jpeg)

##### Converted with a modified version of [MLX](https://github.com/ml-explore/mlx)
##### For more details see our [demonstration videos](https://youtube.com/xcreate) or visit [DeepSeek-V4-Flash-Vision-Exp](https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp).

## Disclaimer

We are not the creator, originator, or owner of any model listed. Each model is created and provided by third parties. Models may not always be accurate or contextually appropriate. You are responsible for verifying the information before making important decisions. We are not liable for any damages, losses, or issues arising from its use, including data loss or inaccuracies in AI-generated content.