--- title: DeepSeek-V4-Flash-Vision-Exp canonical_url: "https://www.modelscope.cn/models/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp" md_url: "https://www.modelscope.cn/models/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp.md" repository: deepseek-ai/DeepSeek-V4-Flash-Vision-Exp last_updated: 2026-09-01 license: mit pipeline_tag: image-text-to-text tasks: - image-text-to-text model_type: - deepseek_v4 architectures: - DeepseekV4ForCausalLM parameters: 304.6B tensor_type: - BF16 - F8_E8M0 - I8 - F8_E4M3 - F32 - I64 library_name: - safetensors - pytorch frameworks: - pytorch supports_inference: txt2txt downloads: 26274 stars: 179 --- # DeepSeek-V4-Flash-Vision-Exp > DeepSeek-V4-Flash-Vision-Exp - deepseek-ai 在 ModelScope 开源的模型。DeepSeek-V4-Flash-Vision-Exp deepseek-ai/DeepSeek-V4-Flash-Vision-Exp 是 ModelScope 魔搭社区上的 304.6B 参数image-text-to-text模型，采用 mit 许可，并支持在线推理（txt2txt）。 - **Repository**: deepseek-ai/DeepSeek-V4-Flash-Vision-Exp - **License**: mit - **Tasks**: image-text-to-text - **Parameters**: 304.6B - **Online inference**: txt2txt - **Downloads**: 26274 - **Stars**: 179 - **Last updated**: 2026-09-01 Source: https://www.modelscope.cn/models/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp --- # DeepSeek-V4-Flash-Vision-Exp
DeepSeek-V4
Homepage Chat
Hugging Face Twitter Follow
License
## 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. ## How to Run with vLLM For example, the command below serves the model with vLLM on a single 4×GB300 node. See the [vLLM recipe](https://recipes.vllm.ai/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp) for detailed instructions and other hardware configurations. ```bash docker run --gpus all \ vllm/vllm-openai:deepseekv4-flash-vision deepseek-ai/DeepSeek-V4-Flash-Vision-Exp \ --kv-cache-dtype fp8 \ --block-size 256 \ --tensor-parallel-size 4 \ --tool-call-parser deepseek_v4 \ --enable-auto-tool-choice \ --reasoning-parser deepseek_v4 \ --reasoning-config '{"reasoning_parser":"deepseek_v4","reasoning_start_str":"","reasoning_end_str":""}' \ --speculative-config '{"method":"dspark","model":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","num_speculative_tokens":3,"draft_sample_method":"probabilistic","enable_adaptive_verification":true}' ``` ## How to Run with SGLang Enable DSpark with --speculative-algorithm DSPARK and do not set a separate --speculative-draft-model-path as the target and draft weights therefore come from the same checkpoint. See the [SGLang cookbook](https://docs.sglang.io/cookbook/autoregressive/DeepSeek/DeepSeek-V4#hw=b200&variant=flash-vision&quant=fp4&strategy=low-latency&nodes=single) for detailed instructions, benchmarks and other hardwares configurations. ``` sglang serve \ --model-path deepseek-ai/DeepSeek-V4-Flash-Vision-Exp \ --tp 4 \ --speculative-algorithm DSPARK \ --mem-fraction-static 0.85 \ --host 0.0.0.0 \ --port 30000 ``` ## License This repository is licensed under the [MIT License](LICENSE).