DE

DeepSeek V4 Flash EXTENSOR

DeepSeekGGUF by amdUpdated 2026-08-06
Download on Hugging Face
Parameters284B
Context1024K
Layers43
Architecturedeepseek4
Smallest quant155.8 GB
Quick answer

DeepSeek V4 Flash EXTENSOR needs about 157.1 GB of memory at MXFP4 (a 155.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 2.9 GB.

DeepSeek V4 Flash EXTENSOR – large‑context, high‑capacity LLM

DeepSeek V4 Flash EXTENSOR is a 284‑billion‑parameter model with a 1,048,576‑token context window. It is released under the MIT license and is quantized to MXFP4. The model is a mixture of experts and includes a speculative decoding module.

Good at

  • Large context generation
  • High‑capacity reasoning
  • Speculative decoding

Limits

  • Requires 157.1 GB VRAM at 8k context
  • No vision support
  • MIT license only

Best for

  • Long‑form content creation
  • Complex reasoning tasks
  • Agentic workflows

Who it’s for. Developers needing a very large context window and high parameter count for advanced reasoning. The model is suitable for research and production environments that can accommodate its memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP4155.8 GB 157.1 GB
Too big Get file →

The only available quant is MXFP4, 155.85 GB. It requires approximately 157.1 GB of VRAM at 8k context. No other quants are provided.

What GPU do you need for DeepSeek V4 Flash EXTENSOR?

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.

Which DeepSeek V4 Flash EXTENSOR quant should you choose?

MXFP4 (155.8 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

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

Source

Quantized byamd
FamilyDeepSeek
Licensemit
Downloads (HF)92
Last updated2026-08-06

Frequently asked questions about DeepSeek V4 Flash EXTENSOR

How much VRAM does DeepSeek V4 Flash EXTENSOR need?

About 157.1 GB at MXFP4 with an 8K context window. That is the 155.8 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 EXTENSOR on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 157.1 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: MXFP4 is 155.8 GB.

What context length does DeepSeek V4 Flash EXTENSOR 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 EXTENSOR GGUF?

The files are on Hugging Face in the amd/DeepSeek-V4-Flash-EXTENSOR 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 EXTENSOR 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 this model on 8 GB VRAM?

No. The model requires about 157.1 GB of VRAM at 8k context.

Is there a smaller quant available?

Only the MXFP4 quant is provided; no smaller quant exists.

Does the model support vision tasks?

No, the model has no vision support.

Other GGUFs of DeepSeek-V4-Flash-0731

Similar models

Browse all →

More from amd

All by amd →

More DeepSeek models

All DeepSeek →

Other large models

All large models →