Model reference · open weights
DeepSeek-Flash-Vision-Exp is an open-weight language model from unsloth. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Maker | unsloth |
|---|---|
| Type | Language models |
| Task | Text gen |
| Parameters (lead) | 304.6B |
| Context | 1024k tokens |
| Runs with | transformers |
| Based on | deepseek-ai/DeepSeek-V4-Flash-Vision-Exp |
| Released | 2026-08-31 |
| Popularity | 0 downloads / month |
| Licence | Open weights |
About
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:
max reasoning effort level with temperature = 1.0, top_p = 0.95.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/ # 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.
See 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.
See inference/README.md for dependency installation,
checkpoint conversion, and TXT/JSON inference commands.
This repository is licensed under the MIT License.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys unsloth-deepseek-flash-vision-exp for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (unsloth-deepseek-flash-vision-exp below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"unsloth-deepseek-flash-vision-exp","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.