DE

DeepSeek V4 Pro 0813

DeepSeekGGUF by qtumUpdated 2026-08-21
Download on Hugging Face
Parameters1570B
Context—
Layers—
Architecture—
Smallest quant1.7 GB
Quick answer

DeepSeek V4 Pro 0813 needs about 417.3 GB of memory at IQ1_M (a 372.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 6 quants, from 1.7 GB to 763.7 GB (Q3_K_M).

DeepSeek V4 Pro 0813 – 1.57T parameter LLM in GGUF format

DeepSeek V4 Pro 0813 is a 1.57 trillion parameter model released by DeepSeek. It is available in several sub‑4‑bit GGUF quantizations produced by qtum. The model is licensed under MIT and supports only text input.

Good at

  • Large context reasoning
  • Agentic task performance
  • High token throughput

Limits

  • Requires large VRAM (hundreds of GB)
  • No vision support
  • No Jinja chat template

Best for

  • Enterprise chatbots
  • Complex coding assistance
  • Long‑form content generation

Who it’s for. Developers and researchers needing a high‑capacity language model for text‑only workloads. The model is suitable for environments with ample GPU memory and where MIT licensing is acceptable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—1.7 GB 2.4 GB
Fits Get file →
IQ1_S337.3 GB 378.2 GB
Too big Get file →
IQ1_M372.1 GB 417.3 GB
Too big Get file →
Q2_K587.3 GB (14 parts) 658.3 GB
Too big Get file →
IQ3_XXS619.5 GB (15 parts) 694.4 GB
Too big Get file →
Q3_K_M763.7 GB (18 parts) 855.9 GB
Too big Get file →

For a 8 GB VRAM budget the model is not feasible. If you have a 16 GB GPU, the smallest quant is IQ1_S (337.26 GB file, 378.2 GB memory). With 32 GB VRAM you can use Q2_K (587.3 GB file, 658.3 GB memory). Larger GPUs are required for higher quality quantizations.

What GPU do you need for DeepSeek V4 Pro 0813?

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: the best quant that fits is the main file (1.7 GB file, about 2.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (1.7 GB file, about 2.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (1.7 GB file, about 2.4 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (1.7 GB file, about 2.4 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (1.7 GB file, about 2.4 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (1.7 GB file, about 2.4 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (1.7 GB file, about 2.4 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (1.7 GB file, about 2.4 GB in use).

Which DeepSeek V4 Pro 0813 quant should you choose?

IQ1_M (372.1 GB) is the middle option in this repository. 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.

If memory is tight, the smallest file is the first one in the table at 1.7 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Parameters1570B

Source

Quantized byqtum
FamilyDeepSeek
Licensemit
Downloads (HF)1,690
Last updated2026-08-21

Frequently asked questions about DeepSeek V4 Pro 0813

How much VRAM does DeepSeek V4 Pro 0813 need?

About 417.3 GB at IQ1_M with an 8K context window. That is the 372.1 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 Pro 0813 on an 8 GB GPU?

Yes, with the smaller files: the 1.7 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DeepSeek V4 Pro 0813 GGUF?

It depends on the quant: file is 1.7 GB, IQ1_S is 337.3 GB, IQ1_M is 372.1 GB, Q2_K is 587.3 GB, IQ3_XXS is 619.5 GB, Q3_K_M is 763.7 GB.

Where can I download DeepSeek V4 Pro 0813 GGUF?

The files are on Hugging Face in the qtum/DeepSeek-V4-Pro-0813-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 Pro 0813 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 Pro 0813 on 8 GB VRAM?

No. The smallest quant requires 378.2 GB of VRAM at 8k context.

What license does the model use?

MIT license.

Does the model support vision or image input?

No, it is a text‑only model.

Other GGUFs of DeepSeek-V4-Pro-0813

Similar models

Browse all →

More from qtum

All by qtum →

More DeepSeek models

All DeepSeek →

Other large models

All large models →