Deepseek v4 needs about 293.0 GB of memory at BF16 (a 291.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. Longer context needs more: at 32K tokens the KV cache alone adds about 2.9 GB.
Deepseek v4 is a 146B-parameter DeepSeek model in GGUF format, quantized by aj969hf. Its trained context length is 1024K tokens. The repository has 1 quant file, from 291.8 GB (BF16) to 291.8 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 291.8 GB | 293.0 GB | Too big | Get file → |
What GPU do you need for Deepseek v4?
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 quant should you choose?
BF16 (291.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Deepseek v4
How much VRAM does Deepseek v4 need?
About 293.0 GB at BF16 with an 8K context window. That is the 291.8 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 293.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Deepseek v4 GGUF?
It depends on the quant: BF16 is 291.8 GB.
What context length does Deepseek v4 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 GGUF?
The files are on Hugging Face in the aj969hf/DeepSeek-V4-Flash-0731-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 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.