DeepSeek V3 Slice Jp64 needs about 150.1 GB of memory at Q4_K_M (a 108.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 47.3 GB (IQ2_XXS) to 127.8 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 163.7 GB.
DeepSeek V3 Slice Jp64 is a 181B-parameter DeepSeek model in GGUF format, quantized by mmnga. Its trained context length is 160K tokens. The repository has 7 quant files, from 47.3 GB (IQ2_XXS) to 127.8 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 47.3 GB (5 parts) | 88.7 GB | Too big | Get file → | |
| IQ2_XS | 52.8 GB (5 parts) | 94.2 GB | Too big | Get file → | |
| IQ2_S | 54.1 GB (5 parts) | 95.6 GB | Too big | Get file → | |
| IQ4_XS | 96.3 GB (9 parts) | 137.7 GB | Too big | Get file → | |
| IQ4_NL | 101.9 GB (10 parts) | 143.3 GB | Too big | Get file → | |
| Q4_K_M | 108.6 GB (11 parts) | 150.1 GB | Too big | Get file → | |
| Q5_K_M | 127.8 GB (12 parts) | 169.2 GB | Too big | Get file → |
What GPU do you need for DeepSeek V3 Slice Jp64?
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 Slice Jp64 quant should you choose?
Q4_K_M is the usual starting point for DeepSeek V3 Slice Jp64: it balances file size and quality well. Here it is a 108.6 GB file.
If memory is tight, the smallest file is IQ2_XXS at 47.3 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 Slice Jp64
How much VRAM does DeepSeek V3 Slice Jp64 need?
About 150.1 GB at Q4_K_M with an 8K context window. That is the 108.6 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 V3 Slice Jp64 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 88.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek V3 Slice Jp64 GGUF?
It depends on the quant: IQ2_XXS is 47.3 GB, IQ2_XS is 52.8 GB, IQ2_S is 54.1 GB, IQ4_XS is 96.3 GB, IQ4_NL is 101.9 GB, Q4_K_M is 108.6 GB and 1 more.
What context length does DeepSeek V3 Slice Jp64 support?
The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 40.9 GB at 8K and 163.7 GB at 32K.
Where can I download DeepSeek V3 Slice Jp64 GGUF?
The files are on Hugging Face in the mmnga/DeepSeek-V3-slice-jp64-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 Slice Jp64 use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.