DeepSeek V4 Flash custom iq3down needs about 103.1 GB of memory at its main file (a 91.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds.
DeepSeek V4 Flash custom iq3down is a 284B-parameter DeepSeek model in GGUF format, quantized by starvingcheetah. Its trained context length is 1024K tokens. The repository has 1 quant file, from 91.6 GB to 91.6 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 91.6 GB (3 parts) | 103.1 GB | Too big | Get file → |
What GPU do you need for DeepSeek V4 Flash custom iq3down?
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.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepSeek V4 Flash custom iq3down
How much VRAM does DeepSeek V4 Flash custom iq3down need?
About 103.1 GB at its main file with an 8K context window. That is the 91.6 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 custom iq3down on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 103.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek V4 Flash custom iq3down GGUF?
It depends on the quant: file is 91.6 GB.
What context length does DeepSeek V4 Flash custom iq3down support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download DeepSeek V4 Flash custom iq3down GGUF?
The files are on Hugging Face in the starvingcheetah/DeepSeek-V4-Flash-custom-iq3down-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 custom iq3down 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.