DeepSeek V4 Flash needs about 150.6 GB of memory at IQ3_XXS (a 134.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 88.0 GB (IQ2_S) to 156.4 GB (Q8_0).
DeepSeek V4 Flash is a 284B-parameter DeepSeek model in GGUF format, quantized by bullerwins. Its trained context length is 1024K tokens. The repository has 7 quant files, from 88.0 GB (IQ2_S) to 156.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_S | 88.0 GB | 99.1 GB | Too big | Get file → | |
| IQ3_XXS | 102.4 GB | 115.2 GB | Too big | Get file → | |
| IQ3_XXS | 114.0 GB | 128.2 GB | Too big | Get file → | |
| IQ3_XXS | 134.1 GB | 150.6 GB | Too big | Get file → | |
| IQ3_XXS | 151.3 GB | 169.9 GB | Too big | Get file → | |
| IQ4_XS | 155.1 GB | 174.2 GB | Too big | Get file → | |
| Q8_0 | 156.4 GB | 175.6 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 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_XXS (134.1 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 IQ2_S at 88.0 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 150.6 GB at IQ3_XXS with an 8K context window. That is the 134.1 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 99.1 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: IQ2_S is 88.0 GB, IQ3_XXS is 102.4 GB, IQ3_XXS is 114.0 GB, IQ3_XXS is 134.1 GB, IQ3_XXS is 151.3 GB, IQ4_XS is 155.1 GB and 1 more.
What context length does DeepSeek V4 Flash support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download DeepSeek V4 Flash GGUF?
The files are on Hugging Face in the bullerwins/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.