DeepSeek-V4-Pro-0813

Model tree for deepseek-ai/DeepSeek-V4-Pro-0813

Finetunes

1 model

Quantizations

14 models

Spaces using deepseek-ai/DeepSeek-V4-Pro-0813 14

Collection including deepseek-ai/DeepSeek-V4-Pro-0813

[

DeepSeek-V4

Collection

10 items • Updated 1 day ago • 900

](https://huggingface.co/collections/deepseek-ai/deepseek-v4)

Paper for deepseek-ai/DeepSeek-V4-Pro-0813

[

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Paper • 2606.19348 • Published Apr 26 • 43

](https://huggingface.co/papers/2606.19348)

Contact

If you have any questions, please raise an issue or contact us at service@deepseek.com.

Safetensors

Model size

1.7T params

Tensor type

BF16

·

I64

·

F32

·

F8_E4M3

·

I8

·

Citation

@misc{deepseekai2026deepseekv4,
      title={DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence},
      author={DeepSeek-AI},
      year={2026},
}

License

This repository and the model weights are licensed under the MIT License.

How to Run Locally

Please refer to the inference folder for detailed instructions on running DeepSeek-V4 locally, including model weight conversion and interactive chat demos.

For local deployment, we recommend setting the sampling parameters to temperature = 1.0, with top_p = 0.95 for agentic scenarios and top_p = 1.0 otherwise. For the high and max reasoning effort levels, we recommend a maximum output length of 384K tokens.

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 for detailed instructions, benchmarks and other hardwares configurations.

sglang serve \
  --trust-remote-code \
  --model-path deepseek-ai/DeepSeek-V4-Pro-0813 \
  --tp 4 \
  --moe-runner-backend flashinfer_mxfp4 \
  --speculative-algorithm DSPARK \
  --mem-fraction-static 0.90 \
  --chunked-prefill-size 4096 \
  --swa-full-tokens-ratio 0.1 \

How to Run with vLLM

DSpark speculative decoding is enabled with a single flag — add --speculative-config with method: dspark to your vLLM launch command:

--speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'

For example, the command below serves the model with vLLM on a single 4×GB300 node. See the vLLM recipe for detailed instructions and other hardware configurations.

vllm serve deepseek-ai/DeepSeek-V4-Pro-0813 \
  --trust-remote-code --kv-cache-dtype fp8 --block-size 256 \
  --data-parallel-size 4 --enable-expert-parallel \
  --moe-backend deep_gemm_mega_moe \
  --attention-config '{"use_fp4_indexer_cache": true}' \
  --speculative-config '{"method":"dspark","num_speculative_tokens":7,"draft_sample_method":"greedy"}'

Chat Template

This release does not include a Jinja-format chat template. Instead, we provide a dedicated encoding folder with Python scripts and test cases demonstrating how to encode messages in OpenAI-compatible format into input strings for the model, and how to parse the model's text output. Please refer to the encoding folder for full documentation.

The reasoning_effort parameter now supports three levels — low, high, and max — which control how much deliberation the model spends before answering.

A brief example:

from encoding_dsv4 import encode_messages, parse_message_from_completion_text

messages = [
    {"role": "user", "content": "hello"},
    {"role": "assistant", "content": "Hello! I am DeepSeek.", "reasoning_content": "thinking..."},
    {"role": "user", "content": "1+1=?"}
]

## messages -> string
prompt = encode_messages(messages, thinking_mode="thinking", reasoning_effort="max")

## string -> tokens
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-V4-Pro-0813")
tokens = tokenizer.encode(prompt)

Introduction

DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in production environments. It is built on the DeepSeek-V4-Pro (Preview) model structure, with a DSpark speculative decoding module attached.

DeepSeek-V4-Pro-0813 outperforms DeepSeek-V4-Pro (Preview) on the benchmarks listed below, and is broadly competitive with the strongest proprietary models available.

Notes:

1. For the code-agent tasks among the public benchmarks above, DeepSeek-V4-Pro-0813 is 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. † DSBench-FullStack is an internal full-stack development test set; DSBench-Hard is an internal test set of difficult coding-agent problems.