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 is a 1570B-parameter DeepSeek model in GGUF format, quantized by 6block. Its trained context length is 1024K tokens. The repository has 6 quant files, from 1.7 GB to 763.7 GB (Q3_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.7 GB | 2.4 GB | Fits | Get file → | |
| IQ1_S | 337.3 GB | 378.2 GB | Too big | Get file → | |
| IQ1_M | 372.1 GB | 417.3 GB | Too big | Get file → | |
| Q2_K | 587.3 GB (14 parts) | 658.3 GB | Too big | Get file → | |
| IQ3_XXS | 619.5 GB (15 parts) | 694.4 GB | Too big | Get file → | |
| Q3_K_M | 763.7 GB (18 parts) | 855.9 GB | Too big | Get file → |
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
Source
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.
What context length does DeepSeek V4 Pro 0813 support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download DeepSeek V4 Pro 0813 GGUF?
The files are on Hugging Face in the 6block/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.