DeepSeek V4 Flash 0731 ROCmFP4 needs about 109.1 GB of memory at its main file (a 107.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 107.9 GB to 151.4 GB (Q4_0). Longer context needs more: at 32K tokens the KV cache alone adds about 3.1 GB.
DeepSeek V4 Flash 0731 ROCmFP4 is a 304B-parameter DeepSeek model in GGUF format, quantized by kingjones777. Its trained context length is 1024K tokens. The repository has 2 quant files, from 107.9 GB to 151.4 GB (Q4_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 107.9 GB (4 parts) | 109.1 GB | Too big | Get file → | |
| Q4_0 | 151.4 GB (4 parts) | 152.6 GB | Too big | Get file → |
What GPU do you need for DeepSeek V4 Flash 0731 ROCmFP4?
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.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepSeek V4 Flash 0731 ROCmFP4
How much VRAM does DeepSeek V4 Flash 0731 ROCmFP4 need?
About 109.1 GB at its main file with an 8K context window. That is the 107.9 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 0731 ROCmFP4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 109.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek V4 Flash 0731 ROCmFP4 GGUF?
It depends on the quant: file is 107.9 GB, Q4_0 is 151.4 GB.
What context length does DeepSeek V4 Flash 0731 ROCmFP4 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 0.8 GB at 8K and 3.1 GB at 32K.
Where can I download DeepSeek V4 Flash 0731 ROCmFP4 GGUF?
The files are on Hugging Face in the kingjones777/DeepSeek-V4-Flash-0731-ROCmFP4 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 0731 ROCmFP4 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.