DE

Deepseek-V4-Flash

DeepSeekGGUF by unslothUpdated 2026-07-09
Download on Hugging Face
Parameters284B
Context1024K
Layers43
Architecturedeepseek4
Smallest quant82.5 GB
Quick answer

Deepseek-V4-Flash needs about 118.5 GB of memory at IQ3_S (a 117.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 82.5 GB (IQ1_S) to 161.9 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 2.9 GB.

DeepSeek‑V4‑Flash: 284B‑parameter MoE model with 1M‑token context

DeepSeek‑V4‑Flash is a 284‑billion‑parameter Mixture‑of‑Experts language model. It supports a context length of one million tokens and is built on the deepseek4 architecture. The model is released under the MIT license.

Good at

  • Large‑context generation
  • Efficient long‑sequence inference
  • Domain‑specific expert knowledge

Limits

  • Requires high VRAM for full precision
  • No vision support
  • Large model size limits deployment on modest hardware

Best for

  • Enterprise chatbots needing long context
  • Research on million‑token inference
  • Fine‑tuning domain experts

Who it’s for. Developers and researchers who need a high‑capacity language model with a million‑token context. The model is suitable for teams with access to GPUs with sufficient VRAM and for projects that can handle large model files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S82.5 GB (3 parts) 83.8 GB
Too big Get file →
IQ1_M86.9 GB (3 parts) 88.1 GB
Too big Get file →
IQ2_XXS90.9 GB (3 parts) 92.1 GB
Too big Get file →
IQ2_M90.9 GB (3 parts) 92.1 GB
Too big Get file →
Q2_K_XL96.8 GB (3 parts) 98.1 GB
Too big Get file →
IQ3_XXS103.0 GB (4 parts) 104.2 GB
Too big Get file →
IQ3_S117.3 GB (4 parts) 118.5 GB
Too big Get file →
Q3_K_M129.3 GB (4 parts) 130.5 GB
Too big Get file →
Q3_K_XL129.4 GB (4 parts) 130.7 GB
Too big Get file →
IQ4_NL137.9 GB (4 parts) 139.1 GB
Too big Get file →
IQ4_XS137.9 GB (4 parts) 139.1 GB
Too big Get file →
Q4_K_XL155.1 GB (5 parts) 156.3 GB
Too big Get file →
Q8_K_XL161.9 GB (5 parts) 163.1 GB
Too big Get file →

For 8‑GB VRAM use IQ1_S or IQ1_M (≈84‑89 GB file, 84‑88 GB memory at 8 k context). For 16‑GB VRAM use IQ2_XXS or IQ2_M (≈91 GB file, 92 GB memory). For 24‑GB VRAM use Q2_K_XL (≈97 GB file, 98 GB memory). For 32‑GB VRAM use Q3_K_M or Q3_K_XL (≈129 GB file, 130 GB memory). Full precision Q8_K_XL requires 162 GB file and 163 GB memory.

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.

Which Deepseek-V4-Flash quant should you choose?

IQ3_S (117.3 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 IQ1_S at 82.5 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

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

Source

Quantized byunsloth
FamilyDeepSeek
Licensemit
Downloads (HF)25,476
Last updated2026-07-09

Frequently asked questions about Deepseek-V4-Flash

How much VRAM does Deepseek-V4-Flash need?

About 118.5 GB at IQ3_S with an 8K context window. That is the 117.3 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 83.8 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: IQ1_S is 82.5 GB, IQ1_M is 86.9 GB, IQ2_XXS is 90.9 GB, IQ2_M is 90.9 GB, Q2_K_XL is 96.8 GB, IQ3_XXS is 103.0 GB and 7 more.

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 unsloth/DeepSeek-V4-Flash-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 8 GB VRAM?

No, the smallest quant requires around 84 GB VRAM. 8 GB is insufficient.

Does DeepSeek‑V4‑Flash support vision tasks?

No, the model has no vision capabilities.

Other GGUFs of DeepSeek-V4-Flash

Similar models

Browse all →

More from unsloth

All by unsloth →

More DeepSeek models

All DeepSeek →

Other large models

All large models →