DE

DeepSeek V4 Flash 0731 ROCmFP3 MIX

DeepSeekGGUF by Geometric-AIUpdated 2026-08-10
Download on Hugging Face
Parameters284B
Context1024K
Layers43
Architecturedeepseek4
Smallest quant98.3 GB
Quick answer

DeepSeek V4 Flash 0731 ROCmFP3 MIX needs about 99.5 GB of memory at its main file (a 98.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 98.3 GB to 102.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.9 GB.

DeepSeek V4 Flash 0731 ROCmFP3 MIX is a 284B-parameter DeepSeek model in GGUF format, quantized by Geometric-AI. Its trained context length is 1024K tokens. The repository has 2 quant files, from 98.3 GB to 102.3 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—98.3 GB 99.5 GB
Too big Get file →
—102.3 GB 103.5 GB
Too big Get file →

What GPU do you need for DeepSeek V4 Flash 0731 ROCmFP3 MIX?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Specifications

Architecture from the GGUF header

Architecturedeepseek4
Parameters284B (approximate, mixture of experts)
Layers43
Trained context1,048,576 tokens
KV cache (fp16)86 KB per token

Source

Quantized byGeometric-AI
FamilyDeepSeek
Licensemit
Downloads (HF)131
Last updated2026-08-10

Frequently asked questions about DeepSeek V4 Flash 0731 ROCmFP3 MIX

How much VRAM does DeepSeek V4 Flash 0731 ROCmFP3 MIX need?

About 99.5 GB at its main file with an 8K context window. That is the 98.3 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 ROCmFP3 MIX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 99.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek V4 Flash 0731 ROCmFP3 MIX GGUF?

It depends on the quant: file is 98.3 GB, file is 102.3 GB.

What context length does DeepSeek V4 Flash 0731 ROCmFP3 MIX support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.9 GB at 32K.

Where can I download DeepSeek V4 Flash 0731 ROCmFP3 MIX GGUF?

The files are on Hugging Face in the Geometric-AI/DeepSeek-V4-Flash-0731-ROCmFP3-MIX 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 ROCmFP3 MIX 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 Geometric-AI

All by Geometric-AI →

More DeepSeek models

All DeepSeek →

Other large models

All large models →