DE

DeepSeek V4 4B Toy

DeepSeekGGUF by Bert504Updated 2026-08-22
Download on Hugging Face
Parameters4.08B
Context1024K
Layers—
Architecturedeepseek4
Smallest quant2.6 GB
Quick answer

DeepSeek V4 4B Toy needs about 3.4 GB of memory at MXFP4 (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU.

DeepSeek V4 4B Toy is a 4.08B-parameter DeepSeek model in GGUF format, quantized by Bert504. Its trained context length is 1024K tokens. The repository has 1 quant file, from 2.6 GB (MXFP4) to 2.6 GB (MXFP4).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
MXFP42.6 GB 3.4 GB
Fits Get file →

What GPU do you need for DeepSeek V4 4B Toy?

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 MXFP4 (2.6 GB file, about 3.4 GB in use).

Which DeepSeek V4 4B Toy quant should you choose?

MXFP4 (2.6 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
Parameters4.08B
Trained context1,048,576 tokens

Source

Quantized byBert504
FamilyDeepSeek
Licensemit
Downloads (HF)46
Last updated2026-08-22

Frequently asked questions about DeepSeek V4 4B Toy

How much VRAM does DeepSeek V4 4B Toy need?

About 3.4 GB at MXFP4 with an 8K context window. That is the 2.6 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 4B Toy on an 8 GB GPU?

Yes, with MXFP4: the 2.6 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of DeepSeek V4 4B Toy GGUF?

It depends on the quant: MXFP4 is 2.6 GB.

What context length does DeepSeek V4 4B Toy support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K).

Where can I download DeepSeek V4 4B Toy GGUF?

The files are on Hugging Face in the Bert504/DeepSeek-V4-4B-Toy 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 4B Toy 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.

Other GGUFs of DeepSeek-V4-Flash-0731

Similar models

Browse all →

More DeepSeek models

All DeepSeek →

Other small models

All small models →