DeepSeek-V3-0324 needs about 149.4 GB of memory at IQ1_S (a 147.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 113.4 GB to 226.1 GB (Q2_K_L). 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 moxin-org. Its trained context length is 160K tokens. The repository has 4 quant files, from 113.4 GB to 226.1 GB (Q2_K_L).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 113.4 GB (4 parts) | 115.0 GB | Too big | Get file → | |
| IQ1_S | 147.8 GB (5 parts) | 149.4 GB | Too big | Get file → | |
| IQ1_M | 162.4 GB (6 parts) | 164.0 GB | Too big | Get file → | |
| Q2_K_L | 226.1 GB (8 parts) | 227.7 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?
IQ1_S (147.8 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 the first one in the table at 113.4 GB, with the quality trade-offs that come with fewer bits.
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 149.4 GB at IQ1_S with an 8K context window. That is the 147.8 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 115.0 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: file is 113.4 GB, IQ1_S is 147.8 GB, IQ1_M is 162.4 GB, Q2_K_L is 226.1 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 moxin-org/DeepSeek-V3-0324-Moxin-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.