deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
image-text-to-text model by deepseek-ai
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
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. Notes: 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. 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…
Read the full model card ↗ · Preview checked 2026-10-30T23:12:06.057Z
Inside the original model card — Document outline
- DeepSeek-V4-Flash-Vision-Exp
- Introduction
- Repository layout
- Prompt encoding
- Minimal inference
- How to Run with vLLM
- How to Run with SGLang
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp is a image-text-to-text model repository published by deepseek-ai on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 636,461
- Cumulative likes
- 934
- Hugging Face trending score
- 3
- Reported safetensors parameters
- 304,646,824,126
- Architecture
- DeepseekV4ForCausalLM
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-08-31T06:16:18.000Z
- Last modified
- 2026-09-01T09:22:10.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-12T06:41:20.176Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.