DeepSeek-V4-Flash-MXFP4-FP8-BF16 needs about 157.3 GB of memory at MXFP4 (a 156.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 156.1 GB (MXFP4) to 158.1 GB (MXFP4). Longer context needs more: at 32K tokens the KV cache alone adds about 2.9 GB.
DeepSeek-V4-Flash-MXFP4-FP8-BF16 is a 284B-parameter DeepSeek model in GGUF format, quantized by 6ms. Its trained context length is 1024K tokens. The repository has 2 quant files, from 156.1 GB (MXFP4) to 158.1 GB (MXFP4).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 156.1 GB | 157.3 GB | Too big | Get file → | |
| MXFP4 | 158.1 GB | 159.3 GB | Too big | Get file → |
What GPU do you need for DeepSeek-V4-Flash-MXFP4-FP8-BF16?
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-Flash-MXFP4-FP8-BF16 quant should you choose?
MXFP4 (156.1 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
Source
Frequently asked questions about DeepSeek-V4-Flash-MXFP4-FP8-BF16
How much VRAM does DeepSeek-V4-Flash-MXFP4-FP8-BF16 need?
About 157.3 GB at MXFP4 with an 8K context window. That is the 156.1 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-Flash-MXFP4-FP8-BF16 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 157.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek-V4-Flash-MXFP4-FP8-BF16 GGUF?
It depends on the quant: MXFP4 is 156.1 GB, MXFP4 is 158.1 GB.
What context length does DeepSeek-V4-Flash-MXFP4-FP8-BF16 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-Flash-MXFP4-FP8-BF16 GGUF?
The files are on Hugging Face in the 6ms/DeepSeek-V4-Flash-MXFP4-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-Flash-MXFP4-FP8-BF16 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.