DeepSeek-V4-Flash-0731-GGUF

Read our How to Run DeepSeek-V4-0731 Guide!#

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

https://github.com/unslothai/unsloth/ https://discord.gg/unsloth https://unsloth.ai/docs/models/deepseek-v4

To run DeepSeek-V4-Flash-0731 in full precision lossless, run Q8 (UD-Q8_K_XL), which is 162GB and only 7GB bigger than Q4 (UD-Q4_K_XL).

See our DeepSeek-V4 guide for quantization analysis and instructions.

You can now run DeepSeek-V4-Flash-0731 in Unsloth Studio with toggles for High and Max thinking.

New DSpark support allowing up to 2x faster decodingImage: Docs for DSpark

Image: deepseek-v4-flash-0731 in unsloth studio

DeepSeek-V4-Flash-0731#

Image: DeepSeek-V4

Homepage Chat

Hugging Face Twitter Follow

License

Technical Report👁️

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.

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.

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},
}