---
title: DeepSeek-V4-Flash-Vision-Exp
canonical_url: "https://www.modelscope.cn/models/unsloth/DeepSeek-V4-Flash-Vision-Exp"
md_url: "https://www.modelscope.cn/models/unsloth/DeepSeek-V4-Flash-Vision-Exp.md"
repository: unsloth/DeepSeek-V4-Flash-Vision-Exp
last_updated: 2026-09-01
license: mit
model_type:
- deepseek_v4
architectures:
- DeepseekV4ForCausalLM
base_model:
- deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
base_model_relation: quantized
parameters: 304.6B
tensor_type:
- BF16
- F32
- F8_E4M3
- I64
- F8_E8M0
- I8
library_name:
- safetensors
- pytorch
frameworks:
- pytorch
downloads: 100
stars: 4
tags:
- unsloth
---
# DeepSeek-V4-Flash-Vision-Exp
> DeepSeek-V4-Flash-Vision-Exp - unsloth 在 ModelScope 开源的模型。Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.
unsloth/DeepSeek-V4-Flash-Vision-Exp 是 ModelScope 魔搭社区上的 304.6B 参数机器学习模型，采用 mit 许可，基于 deepseek-ai/DeepSeek-V4-Flash-Vision-Exp 构建。
- **Repository**: unsloth/DeepSeek-V4-Flash-Vision-Exp
- **License**: mit
- **Parameters**: 304.6B
- **Base model**: deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
- **Tags**: unsloth
- **Downloads**: 100
- **Stars**: 4
- **Last updated**: 2026-09-01
Source: https://www.modelscope.cn/models/unsloth/DeepSeek-V4-Flash-Vision-Exp
---
# DeepSeek-V4-Flash-Vision-Exp
## Introduction
We are excited to introduce **DeepSeek-V4-Flash-Vision-Exp**, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.
Compared to DeepSeek-V4-Flash-0731, DeepSeek-V4-Flash-Vision-Exp achieves substantial improvements on its multimodal agent capabilities, while maintaining comparable performance on text-only agent tasks.
| Benchmark | DeepSeek-V4-Flash-Vision-Exp | DeepSeek-V4-Flash-0731 | Opus-4.8 |
| :--- | :---: | :---: | :---: |
| **Text Agent Capabilities** | | | |
| Terminal Bench 2.1 | 83.9 | 82.7 | 85.0 |
| NL2Repo | 57.7 | 54.2 | 69.7 |
| Cybergym | 75.3 | 76.7 | 78.3 |
| DeepSWE | 59.3 | 54.4 | 58.0 |
| Toolathlon-Verified | 75.9 | 70.3 | 76.2 |
| DSBench-Hard | 63.6 | 59.6 | 71.7 |
| AutomationBench (Public) | 25.7 | 25.1 | 27.2 |
| **Multimodal Agent Capabilities** | | | |
| ApexBench (Pass@1) | 36.5 | 26.2† | 39.4 |
| Agents' Last Exam | 27.3 | 25.2† | 25.7 |
| Chartography | 64.3 | - | 65.0 |
| ZeroBench (Pass@5) | 35.0 | - | 34.0 |
Notes:
1. For the text agent benchmarks above, DeepSeek models are evaluated with the minimal mode of DeepSeek Harness as the agent framework, using the `max` reasoning effort level with `temperature = 1.0, top_p = 0.95`.
2. † For ApexBench and Agents' Last Exam, DeepSeek-V4-Flash-0731 ignores the multimodal elements in the input.
## Repository layout
This repository contains the tokenizer, prompt encoding reference, and a
minimal PyTorch inference implementation for DeepSeek-V4 Flash Vision. The
reference inference covers the vision encoder and aligner, DFlash attention,
MoE, Hyper-Connections, and the DSpark forward path.
```text
.
├── encoding/ # OpenAI-style messages -> model prompt
├── inference/ # weight conversion and minimal inference
│ └── examples/ # equivalent TXT and JSON vision prompts
├── config.json # Hugging Face model metadata
├── generation_config.json
├── model.safetensors.index.json
├── tokenizer.json
└── tokenizer_config.json
```
`encoding/` and `inference/` deliberately remain separate: prompt formatting
does not depend on PyTorch, while inference imports the sibling encoding module
with an explicit Python path. No symlinks are required.
The tokenizer files are regular files so that the repository can be uploaded
to Hugging Face without relying on local filesystem symlinks. The large model
shards are described by `model.safetensors.index.json` and are not duplicated
inside the source checkout used to assemble this repository.
## Prompt encoding
See [`encoding/README.md`](encoding/README.md). Both OpenAI-style JSON content
blocks and the compact `path` TXT notation are supported. The two
examples under `inference/examples/` encode to identical prompts and token IDs.
## Minimal inference
See [`inference/README.md`](inference/README.md) for dependency installation,
checkpoint conversion, and TXT/JSON inference commands.
## License
This repository is licensed under the [MIT License](LICENSE).
