DeepSeek V4 Flash 0731 needs about 89.9 GB of memory at IQ2_XXS (a 79.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 8 quants, from 10.9 GB (BF16) to 139.5 GB (Q3_K_M).
DeepSeek V4 Flash 0731 – 284B parameter LLM with DSpark speculative decoding
DeepSeek V4 Flash 0731 is a 284‑billion‑parameter model in the DeepSeek family. It uses the dflash architecture and includes a DSpark speculative‑decoding module. The model is released under an MIT license and is available in multiple GGUF quantizations.
Good at
- Large‑context reasoning
- Agentic coding tasks
- Multilingual text generation
Limits
- No vision support
- Requires 8‑k context for estimates
- No Q8_0 or Q6_K quantizations
Best for
- Chatbots needing deep reasoning
- Code generation agents
- Research prototyping
Who it’s for. Engineers and researchers who need a high‑capacity language model that can run locally with GGUF support. The model is suitable for developers who prefer open‑source licensing and can manage the memory requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| BF16 | 10.9 GB | 12.7 GB | Too big | Get file → | |
| IQ1_S | 63.1 GB (4 parts) | 71.2 GB | Too big | Get file → | |
| IQ1_M | 69.4 GB (4 parts) | 78.2 GB | Too big | Get file → | |
| IQ2_XXS | 79.8 GB (4 parts) | 89.9 GB | Too big | Get file → | |
| IQ2_XS | 88.1 GB (4 parts) | 99.2 GB | Too big | Get file → | |
| Q2_K | 107.9 GB (4 parts) | 121.3 GB | Too big | Get file → | |
| IQ3_XXS | 113.7 GB (4 parts) | 127.8 GB | Too big | Get file → | |
| Q3_K_M | 139.5 GB (4 parts) | 156.7 GB | Too big | Get file → |
For 8‑GB VRAM use the IQ1_S quantization (63.15 GB file, ~71.2 GB memory at 8k context). For 16‑GB VRAM the Q2_K quantization (107.89 GB file, ~121.3 GB memory) is a good balance. If memory is abundant, the BF16 quantization (10.9 GB file, ~12.7 GB memory) offers the best accuracy.
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: 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: the best quant that fits is BF16 (10.9 GB file, about 12.7 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (10.9 GB file, about 12.7 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (10.9 GB file, about 12.7 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (10.9 GB file, about 12.7 GB in use).
Which DeepSeek V4 Flash 0731 quant should you choose?
IQ2_XXS (79.8 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
If memory is tight, the smallest file is BF16 at 10.9 GB, with the quality trade-offs that come with fewer bits. 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 Flash 0731
How much VRAM does DeepSeek V4 Flash 0731 need?
About 89.9 GB at IQ2_XXS with an 8K context window. That is the 79.8 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 Flash 0731 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek V4 Flash 0731 GGUF?
It depends on the quant: BF16 is 10.9 GB, IQ1_S is 63.1 GB, IQ1_M is 69.4 GB, IQ2_XXS is 79.8 GB, IQ2_XS is 88.1 GB, Q2_K is 107.9 GB and 2 more.
Where can I download DeepSeek V4 Flash 0731 GGUF?
The files are on Hugging Face in the 6block/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?
The smallest quantization that fits 8 GB VRAM is IQ1_S, which requires about 71.2 GB of memory at 8k context, so it will not fit. A larger VRAM budget is needed.
Does the model support vision inputs?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the MIT license.