DeepSeek V4 Flash 0731 needs about 128.0 GB of memory at IQ3_XXS (a 113.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 0.5 GB to 161.9 GB (MXFP4_MOE).
DeepSeek V4 Flash 0731 – 284B parameter LLM with speculative decoding
DeepSeek V4 Flash 0731 is a 284B parameter model that supports speculative decoding via DSpark. It is released under the MIT license and offers a range of quantizations for different memory budgets. The model is available in GGUF format for llama.cpp.
Good at
- Speculative decoding
- Large context handling
- Agentic reasoning
Limits
- No vision support
- No external benchmark data provided
- Requires 8k context for memory estimates
Best for
- Chat applications
- Coding agent tasks
- Research prototyping
Who it’s for. Developers and researchers who need a large language model with speculative decoding and a variety of quantization options. The model is suitable for local deployment on systems with sufficient VRAM and RAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.5 GB | 1.0 GB | Fits | Get file → | |
| — | 10.9 GB | 12.7 GB | Too big | Get file → | |
| IQ2_XS | 87.9 GB | 98.9 GB | Too big | Get file → | |
| IQ3_XXS | 113.9 GB | 128.0 GB | Too big | Get file → | |
| IQ2_XS | 120.3 GB | 135.3 GB | Too big | Get file → | |
| IQ3_S | 126.9 GB | 142.6 GB | Too big | Get file → | |
| MXFP4_MOE | 156.4 GB | 175.6 GB | Too big | Get file → | |
| MXFP4_MOE | 161.9 GB | 181.8 GB | Too big | Get file → |
For 8 GB VRAM, use the 0.47 GB file (est. 1 GB memory at 8k context). For 16 GB VRAM, the 10.9 GB file (est. 12.7 GB) is suitable. For larger memory budgets, the 87.9 GB IQ2_XS (est. 98.9 GB) or 113.87 GB IQ3_XXS (est. 128 GB) files provide higher quality.
What GPU do you need for DeepSeek V4 Flash 0731?
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 the main file (0.5 GB file, about 1.0 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 1.0 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 12.7 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 12.7 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 12.7 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (10.9 GB file, about 12.7 GB in use).
Which DeepSeek V4 Flash 0731 quant should you choose?
IQ3_XXS (113.9 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is the first one in the table at 0.5 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepSeek V4 Flash 0731
How much VRAM does DeepSeek V4 Flash 0731 need?
About 128.0 GB at IQ3_XXS with an 8K context window. That is the 113.9 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 on an 8 GB GPU?
Yes, with the smaller files: the 0.5 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeepSeek V4 Flash 0731 GGUF?
It depends on the quant: file is 0.5 GB, file is 10.9 GB, IQ2_XS is 87.9 GB, IQ3_XXS is 113.9 GB, IQ2_XS is 120.3 GB, IQ3_S is 126.9 GB and 2 more.
Where can I download DeepSeek V4 Flash 0731 GGUF?
The files are on Hugging Face in the bullerwins/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 Flash 0731 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.
Can I run DeepSeek V4 Flash 0731 on 8 GB VRAM?
Yes, the 0.47 GB GGUF file requires approximately 1 GB of VRAM at 8k context, which fits within an 8 GB VRAM budget.
What quantization gives the best quality?
The IQ3_XXS and IQ3_S quantizations offer higher quality, but require larger memory footprints.
Is the model licensed for commercial use?
The model is released under the MIT license, which permits commercial use.