DeepSeek V4 Flash MTP support needs about 97.6 GB of memory at its main file (a 86.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 3.8 GB (Q8_0) to 164.6 GB.
DeepSeek V4 Flash MTP support is a 284B-parameter DeepSeek model in GGUF format, quantized by eadx. Its trained context length is 1024K tokens. The repository has 3 quant files, from 3.8 GB (Q8_0) to 164.6 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 3.8 GB | 4.8 GB | Fits | Get file → | |
| — | 86.7 GB | 97.6 GB | Too big | Get file → | |
| — | 164.6 GB | 184.9 GB | Too big | Get file → |
What GPU do you need for DeepSeek V4 Flash MTP support?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.8 GB in use).
Which DeepSeek V4 Flash MTP support quant should you choose?
If memory is tight, the smallest file is Q8_0 at 3.8 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepSeek V4 Flash MTP support
How much VRAM does DeepSeek V4 Flash MTP support need?
About 97.6 GB at its main file with an 8K context window. That is the 86.7 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 MTP support on an 8 GB GPU?
Yes, with Q8_0: the 3.8 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeepSeek V4 Flash MTP support GGUF?
It depends on the quant: Q8_0 is 3.8 GB, file is 86.7 GB, file is 164.6 GB.
What context length does DeepSeek V4 Flash MTP support support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download DeepSeek V4 Flash MTP support GGUF?
The files are on Hugging Face in the eadx/deepseek-v4-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.