Deepseek-V4-Flash needs about 118.5 GB of memory at IQ3_S (a 117.3 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 13 quants, from 82.5 GB (IQ1_S) to 161.9 GB (Q8_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 2.9 GB.
Deepseek-V4-Flash is a 284B-parameter DeepSeek model in GGUF format, quantized by poppingstar. Its trained context length is 1024K tokens. The repository has 13 quant files, from 82.5 GB (IQ1_S) to 161.9 GB (Q8_K_XL).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 82.5 GB (3 parts) | 83.8 GB | Too big | Get file → | |
| IQ1_M | 86.9 GB (3 parts) | 88.1 GB | Too big | Get file → | |
| IQ2_XXS | 90.9 GB (3 parts) | 92.1 GB | Too big | Get file → | |
| IQ2_M | 90.9 GB (3 parts) | 92.1 GB | Too big | Get file → | |
| Q2_K_XL | 96.8 GB (3 parts) | 98.1 GB | Too big | Get file → | |
| IQ3_XXS | 103.0 GB (4 parts) | 104.2 GB | Too big | Get file → | |
| IQ3_S | 117.3 GB (4 parts) | 118.5 GB | Too big | Get file → | |
| Q3_K_M | 129.3 GB (4 parts) | 130.5 GB | Too big | Get file → | |
| Q3_K_XL | 129.4 GB (4 parts) | 130.7 GB | Too big | Get file → | |
| IQ4_NL | 137.9 GB (4 parts) | 139.1 GB | Too big | Get file → | |
| IQ4_XS | 137.9 GB (4 parts) | 139.1 GB | Too big | Get file → | |
| Q4_K_XL | 155.1 GB (5 parts) | 156.3 GB | Too big | Get file → | |
| Q8_K_XL | 161.9 GB (5 parts) | 163.1 GB | Too big | Get file → |
What GPU do you need for Deepseek-V4-Flash?
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 quant should you choose?
IQ3_S (117.3 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 IQ1_S at 82.5 GB, with the quality trade-offs that come with fewer bits. 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Deepseek-V4-Flash
How much VRAM does Deepseek-V4-Flash need?
About 118.5 GB at IQ3_S with an 8K context window. That is the 117.3 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 83.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Deepseek-V4-Flash GGUF?
It depends on the quant: IQ1_S is 82.5 GB, IQ1_M is 86.9 GB, IQ2_XXS is 90.9 GB, IQ2_M is 90.9 GB, Q2_K_XL is 96.8 GB, IQ3_XXS is 103.0 GB and 7 more.
What context length does Deepseek-V4-Flash 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 GGUF?
The files are on Hugging Face in the poppingstar/DeepSeek-V4-Flash-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 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.