Deepseek-V3-0324 needs about 411.4 GB of memory at Q4_K_M (a 409.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 139.5 GB (IQ1_S) to 409.8 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Deepseek-V3-0324 is a 671B-parameter DeepSeek model in GGUF format, quantized by bobchenyx. Its trained context length is 160K tokens. The repository has 4 quant files, from 139.5 GB (IQ1_S) to 409.8 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 139.5 GB (9 parts) | 141.1 GB | Too big | Get file → | |
| IQ1_M | 154.9 GB (9 parts) | 156.5 GB | Too big | Get file → | |
| Q2_K | 238.4 GB (9 parts) | 240.0 GB | Too big | Get file → | |
| Q4_K_M | 409.8 GB (9 parts) | 411.4 GB | Too big | Get file → |
What GPU do you need for Deepseek-V3-0324?
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-V3-0324 quant should you choose?
Q4_K_M is the usual starting point for Deepseek-V3-0324: it balances file size and quality well. Here it is a 409.8 GB file.
If memory is tight, the smallest file is IQ1_S at 139.5 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-V3-0324
How much VRAM does Deepseek-V3-0324 need?
About 411.4 GB at Q4_K_M with an 8K context window. That is the 409.8 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-V3-0324 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 141.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Deepseek-V3-0324 GGUF?
It depends on the quant: IQ1_S is 139.5 GB, IQ1_M is 154.9 GB, Q2_K is 238.4 GB, Q4_K_M is 409.8 GB.
What context length does Deepseek-V3-0324 support?
The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Deepseek-V3-0324 GGUF?
The files are on Hugging Face in the bobchenyx/DeepSeek-V3-0324-MLA-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-V3-0324 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.