DE

DeepSeek V4 Flash

DeepSeekGGUF by twaggs88Updated 2026-08-28
Download on Hugging Face
Parameters240B
Context1024K
Layers43
Architecturedeepseek4
Smallest quant92.5 GB
Quick answer

DeepSeek V4 Flash needs about 93.7 GB of memory at its main file (a 92.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 92.5 GB to 92.8 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 2.9 GB.

DeepSeek V4 Flash – 240B MoE LLM with 1M context

DeepSeek V4 Flash is a 240B parameter model with 1M token context. It supports reasoning and tool usage. The model is released under the MIT license and is available as a single 92.8 GB GGUF file.

Good at

  • Large context reasoning
  • Tool integration
  • High‑capacity language modeling

Limits

  • Requires 128 GB unified memory
  • Only runs on the pulsar engine
  • No vision support

Best for

  • Research on long‑form generation
  • Complex reasoning tasks
  • Tool‑enabled workflows

Who it’s for. Researchers and developers needing a massive language model with extended context. The model is suitable for environments with high VRAM capacity and the pulsar engine.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—92.5 GB 93.7 GB
Too big Get file →
—92.8 GB 94.0 GB
Too big Get file →

The released GGUF file is unquantized and requires approximately 94 GB of memory at 8 k context. For lower VRAM budgets, no alternative quantized versions are provided in the file list.

What GPU do you need for DeepSeek V4 Flash?

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
Parameters240B (approximate, mixture of experts)
Layers43
Trained context1,048,576 tokens
KV cache (fp16)86 KB per token

Source

Quantized bytwaggs88
FamilyDeepSeek
Licensemit
Downloads (HF)921
Last updated2026-08-28

Frequently asked questions about DeepSeek V4 Flash

How much VRAM does DeepSeek V4 Flash need?

About 93.7 GB at its main file with an 8K context window. That is the 92.5 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 93.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek V4 Flash GGUF?

It depends on the quant: file is 92.5 GB, file is 92.8 GB.

What context length does DeepSeek V4 Flash 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 GGUF?

The files are on Hugging Face in the twaggs88/DeepSeek-V4-Flash-REAP25-DSpark-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 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 on 128 GB VRAM?

Yes. The model is designed to fit fully resident on an NVIDIA GB10 with 128 GB unified memory, leaving room for deep context.

Does the model support vision tasks?

No. The model has no vision capabilities.

What engine is required to run this model?

It runs only on the pulsar engine and is not compatible with llama.cpp or other GGUF loaders.

Similar models

Browse all →

More DeepSeek models

All DeepSeek →

Other large models

All large models →