deepseek-ai / DeepSeek-V4-Flash-0731 like 886 Follow DeepSeek 139k
DeepSeek-V4-Flash-0731
---
Introduction
DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities. It has the same model structure as DeepSeek-V4-Flash-DSpark, i.e. it comes with a speculative decoding module attached.
DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.
| Benchmark | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Flash (Preview) | DeepSeek-V4-Pro (Preview) | GLM-5.2 | Opus-4.8 | | ---------------------- | ---------------------- | --------------------------- | ------------------------- | ------- | -------- | | Terminal Bench 2.1 | 82.7 | 61.8 | 72.1 | 81.0 | 85.0 | | NL2Repo | 54.2 | 39.4 | 38.5 | 48.9 | 69.7 | | Cybergym | 76.7 | 38.7 | 52.7 | \- | 83.1 | | DeepSWE | 54.4 | 7.3 | 12.8 | 46.2 | 58.0 | | Toolathlon-Verified | 70.3 | 49.7 | 55.9 | 59.9 | 76.2 | | Agents' Last Exam | 25.2 | 15.8 | 16.5 | 23.8 | 25.7 | | AutomationBench Public | 25.1 | 10.8 | 12.8 | 12.9 | 27.2 | | DSBench-FullStack † | 68.7 | 37.0 | 41.8 | 61.8 | 71.6 | | DSBench-Hard † | 59.6 | 25.8 | 31.1 | 54.5 | 71.7 |
Notes:
1. For the Code Agent tasks among the public benchmarks above, DeepSeek-V4-Flash-0731 is evaluated with the minimal mode of DeepSeek Harness (to be released) 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.
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_textmessages = [
{"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-Flash-0731")
tokens = tokenizer.encode(prompt)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-Flash-0731 \
--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"}'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.
License
This repository and the model weights are licensed under the MIT License.
Citation
@misc{deepseekai2026deepseekv4,
title={DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence},
author={DeepSeek-AI},
year={2026},
}Contact
If you have any questions, please raise an issue or contact us at service@deepseek.com.
Downloads last month -
Safetensors[](https://huggingface.co/docs/safetensors)
Model size
304B params
Tensor type
BF16
·
I64
·
F32
·
F8\_E4M3
·
I8
·
Files info
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 27 Ask for provider support
Model tree for deepseek-ai/DeepSeek-V4-Flash-0731 [](https://huggingface.co/docs/hub/model-cards#specifying-a-base-model)
Finetunes
Quantizations
[](https://huggingface.co/models?apps=llama.cpp&other=base%5Fmodel:quantized:deepseek-ai/DeepSeek-V4-Flash-0731 "Use with llama.cpp")[](https://huggingface.co/models?apps=lmstudio&other=base%5Fmodel:quantized:deepseek-ai/DeepSeek-V4-Flash-0731 "Use with LM Studio")[](https://huggingface.co/models?apps=jan&other=base%5Fmodel:quantized:deepseek-ai/DeepSeek-V4-Flash-0731 "Use with Jan")[](https://huggingface.co/models?apps=ollama&other=base%5Fmodel:quantized:deepseek-ai/DeepSeek-V4-Flash-0731 "Use with Ollama")
Spaces using deepseek-ai/DeepSeek-V4-Flash-0731 2
Collection including deepseek-ai/DeepSeek-V4-Flash-0731
7 items • Updated about 8 hours ago • 772