DE

DeepSeek V4 Flash 0731

DeepSeekGGUF by bartowskiUpdated 2026-08-04
Download on Hugging Face
Parameters284B
Context—
Layers—
Architecturedflash
Smallest quant10.9 GB
Quick answer

DeepSeek V4 Flash 0731 needs about 12.7 GB of memory at MXFP4 (a 10.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 10.9 GB (MXFP4) to 156.4 GB (MXFP4).

DeepSeek V4 Flash 0731 – 284B text‑only LLM in MXFP4

DeepSeek V4 Flash 0731 is a 284B parameter model released under the MIT license. It supports text input only and includes a speculative decoding module. The model is available in MXFP4 quantization with two file sizes.

Good at

  • Large context handling
  • Speculative decoding with DSpark
  • Text‑only generation

Limits

  • No vision support
  • No chat template provided
  • Requires llama.cpp b10173 or newer

Best for

  • Chatbots needing fast inference
  • Agentic coding tasks
  • Research on speculative decoding

Who it’s for. Developers and researchers who need a large‑parameter text model with speculative decoding. The model is suitable for local deployment using llama.cpp or compatible inference engines.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP410.9 GB 12.7 GB
Too big Get file →
MXFP4156.4 GB (4 parts) 175.6 GB
Too big Get file →

For 8‑GB VRAM, use the 10.9‑GB MXFP4 file (≈12.7‑GB memory at 8k context). For larger GPUs, the 156.38‑GB MXFP4 shard set (≈175.6‑GB memory at 8k context) can be used, split into four shards.

What GPU do you need for DeepSeek V4 Flash 0731?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is MXFP4 (10.9 GB file, about 12.7 GB in use).
  • 24 GB VRAM: the best quant that fits is MXFP4 (10.9 GB file, about 12.7 GB in use).
  • 32 GB VRAM: the best quant that fits is MXFP4 (10.9 GB file, about 12.7 GB in use).
  • 48 GB VRAM: the best quant that fits is MXFP4 (10.9 GB file, about 12.7 GB in use).

Which DeepSeek V4 Flash 0731 quant should you choose?

MXFP4 (10.9 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters284B

Source

Quantized bybartowski
FamilyDeepSeek
Licensemit
Downloads (HF)1,097
Last updated2026-08-04

Frequently asked questions about DeepSeek V4 Flash 0731

How much VRAM does DeepSeek V4 Flash 0731 need?

About 12.7 GB at MXFP4 with an 8K context window. That is the 10.9 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: MXFP4 is 10.9 GB, MXFP4 is 156.4 GB.

Where can I download DeepSeek V4 Flash 0731 GGUF?

The files are on Hugging Face in the bartowski/DeepSeek-V4-Flash-0731-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 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.

Can I run DeepSeek V4 Flash 0731 on 8 GB VRAM?

Use the 10.9‑GB MXFP4 file; it requires about 12.7‑GB memory at 8k context, so 8 GB VRAM is insufficient.

Does the model support image input?

No, the model only supports text input.

What inference engines can run this model?

llama.cpp (b10173 or newer), LM Studio, koboldcpp, ramalama, Jan AI, Text Generation Web UI, LoLLMs, Atomic Chat.

Other GGUFs of DeepSeek-V4-Flash-0731

Similar models

Browse all →

More from bartowski

All by bartowski →

More DeepSeek models

All DeepSeek →

Other large models

All large models →