DE

DeepSeek V4 Flash 0731 ds4

DeepSeekGGUF by nazeshinjiteUpdated 2026-08-02
Download on Hugging Face
Parameters19.8B
Context—
Layers—
Architecturedeepseek4-dspark
Smallest quant8.4 GB
Quick answer

DeepSeek V4 Flash 0731 ds4 needs about 97.6 GB of memory at its main file (a 86.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 8.4 GB to 164.6 GB.

DeepSeek V4 Flash 0731 ds4 is a 19.8B-parameter DeepSeek model in GGUF format, quantized by nazeshinjite. The repository has 5 quant files, from 8.4 GB to 164.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.4 GB 9.9 GB
Too big Get file →
—11.4 GB 13.3 GB
Too big Get file →
—86.7 GB 97.6 GB
Too big Get file →
—97.6 GB 109.8 GB
Too big Get file →
—164.6 GB 184.9 GB
Too big Get file →

What GPU do you need for DeepSeek V4 Flash 0731 ds4?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is the main file (8.4 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (11.4 GB file, about 13.3 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (11.4 GB file, about 13.3 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (11.4 GB file, about 13.3 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (11.4 GB file, about 13.3 GB in use).

Which DeepSeek V4 Flash 0731 ds4 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 8.4 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek4-dspark
Parameters19.8B

Source

Quantized bynazeshinjite
FamilyDeepSeek
Licensemit
Downloads (HF)152
Last updated2026-08-02

Frequently asked questions about DeepSeek V4 Flash 0731 ds4

How much VRAM does DeepSeek V4 Flash 0731 ds4 need?

About 97.6 GB at its main file with an 8K context window. That is the 86.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run DeepSeek V4 Flash 0731 ds4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek V4 Flash 0731 ds4 GGUF?

It depends on the quant: file is 8.4 GB, file is 11.4 GB, file is 86.7 GB, file is 97.6 GB, file is 164.6 GB.

Where can I download DeepSeek V4 Flash 0731 ds4 GGUF?

The files are on Hugging Face in the nazeshinjite/DeepSeek-V4-Flash-0731-ds4-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does DeepSeek V4 Flash 0731 ds4 use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of DeepSeek-V4-Flash-0731

Similar models

Browse all →

More from nazeshinjite

All by nazeshinjite →

More DeepSeek models

All DeepSeek →

Other medium models

All medium models →