DeepSeek V4 Flash 0731 needs about 110.9 GB of memory at Q2_K_S (a 98.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 10.8 GB (MXFP4) to 155.0 GB (MXFP4).
DeepSeek V4 Flash 0731 – 284 billion‑parameter LLM with speculative decoding
DeepSeek V4 Flash 0731 is a 284 billion‑parameter model in the DeepSeek family. It uses a dflash architecture and includes a speculative decoding module. The model is released under an MIT license and is available in several GGUF quantizations.
Good at
- Speculative decoding with DSpark
- Large context handling
- Agentic reasoning
Limits
- No vision support
- Requires 8 k context for estimates
- Large memory footprint for high‑precision quants
Best for
- Chat applications needing fast responses
- Coding agent tasks
- Development assistance
Who it’s for. Developers and researchers who need a high‑capacity language model with speculative decoding. The model is suitable for local deployment on GPUs with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 10.8 GB | 12.6 GB | Too big | Get file → | |
| BF16 | 10.9 GB | 12.7 GB | Too big | Get file → | |
| Q2_K_S | 98.6 GB (2 parts) | 110.9 GB | Too big | Get file → | |
| Q2_K | 117.3 GB (2 parts) | 131.9 GB | Too big | Get file → | |
| MXFP4 | 155.0 GB (2 parts) | 174.1 GB | Too big | Get file → |
For 8 GB VRAM, use MXFP4 (10.83 GB file, 12.6 GB memory at 8 k context). For 12 GB VRAM, BF16 (10.9 GB file, 12.7 GB memory). For larger budgets, Q2_K_S (98.59 GB file, 110.9 GB memory) or Q2_K (117.35 GB file, 131.9 GB memory) are available, split into two shards.
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?
Q2_K_S (98.6 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 MXFP4 at 10.8 GB, with the quality trade-offs that come with fewer bits. 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 0731
How much VRAM does DeepSeek V4 Flash 0731 need?
About 110.9 GB at Q2_K_S with an 8K context window. That is the 98.6 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 12.6 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: MXFP4 is 10.8 GB, BF16 is 10.9 GB, Q2_K_S is 98.6 GB, Q2_K is 117.3 GB, MXFP4 is 155.0 GB.
Where can I download DeepSeek V4 Flash 0731 GGUF?
The files are on Hugging Face in the ggml-org/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 MXFP4 quant uses 10.83 GB file size and estimates 12.6 GB memory at 8 k context, which fits within 8 GB VRAM with some overhead.
Does the model support vision tasks?
No, the model does not include vision capabilities.
What license does the model use?
The model is released under the MIT license.