DE

DeepSeek V4 Flash 0731 Pruned 155B A13B

DeepSeekGGUF by takanori-ishikawaUpdated 2026-09-02
Download on Hugging Face
Parameters155B
Context1024K
Layers—
Architecturedflash
Smallest quant1.2 GB
Quick answer

DeepSeek V4 Flash 0731 Pruned 155B A13B needs about 66.6 GB of memory at IQ3_XXS (a 59.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 1.2 GB (IQ2_XXS) to 104.2 GB (IQ3_XXS).

DeepSeek V4 Flash 0731 Pruned 155B A13B is a 155B-parameter DeepSeek model in GGUF format, quantized by takanori-ishikawa. Its trained context length is 1024K tokens. The repository has 3 quant files, from 1.2 GB (IQ2_XXS) to 104.2 GB (IQ3_XXS).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS1.2 GB 1.8 GB
Fits Get file →
IQ3_XXS59.1 GB (2 parts) 66.6 GB
Too big Get file →
IQ3_XXS104.2 GB (3 parts) 117.2 GB
Too big Get file →

What GPU do you need for DeepSeek V4 Flash 0731 Pruned 155B A13B?

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: the best quant that fits is IQ2_XXS (1.2 GB file, about 1.8 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ2_XXS (1.2 GB file, about 1.8 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_XXS (1.2 GB file, about 1.8 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (1.2 GB file, about 1.8 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_XXS (1.2 GB file, about 1.8 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ2_XXS (1.2 GB file, about 1.8 GB in use).
  • 32 GB VRAM: the best quant that fits is IQ2_XXS (1.2 GB file, about 1.8 GB in use).
  • 48 GB VRAM: the best quant that fits is IQ2_XXS (1.2 GB file, about 1.8 GB in use).

Which DeepSeek V4 Flash 0731 Pruned 155B A13B quant should you choose?

IQ3_XXS (59.1 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ2_XXS at 1.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters155B
Trained context1,048,576 tokens

Source

Quantized bytakanori-ishikawa
FamilyDeepSeek
Licensemit
Downloads (HF)785
Last updated2026-09-02

Frequently asked questions about DeepSeek V4 Flash 0731 Pruned 155B A13B

How much VRAM does DeepSeek V4 Flash 0731 Pruned 155B A13B need?

About 66.6 GB at IQ3_XXS with an 8K context window. That is the 59.1 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 Pruned 155B A13B on an 8 GB GPU?

Yes, with IQ2_XXS: the 1.2 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DeepSeek V4 Flash 0731 Pruned 155B A13B GGUF?

It depends on the quant: IQ2_XXS is 1.2 GB, IQ3_XXS is 59.1 GB, IQ3_XXS is 104.2 GB.

What context length does DeepSeek V4 Flash 0731 Pruned 155B A13B support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download DeepSeek V4 Flash 0731 Pruned 155B A13B GGUF?

The files are on Hugging Face in the takanori-ishikawa/DeepSeek-V4-Flash-0731-Pruned-155B-A13B-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 Pruned 155B A13B 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 takanori-ishikawa

All by takanori-ishikawa →

More DeepSeek models

All DeepSeek →

Other large models

All large models →