CodeFuse DeepSeek 33B iMat needs about 17.1 GB of memory at IQ3_S (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 12.9 GB (IQ3_XXS) to 35.4 GB (Q8_0).
CodeFuse DeepSeek 33B iMat is a 33.3B-parameter DeepSeek model in GGUF format, quantized by dranger003. Its trained context length is 16K tokens. The repository has 6 quant files, from 12.9 GB (IQ3_XXS) to 35.4 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 12.9 GB | 15.4 GB | Too big | Get file → | |
| IQ3_XS | 13.6 GB | 16.2 GB | Too big | Get file → | |
| IQ3_S | 14.5 GB | 17.1 GB | Too big | Get file → | |
| IQ3_M | 15.0 GB | 17.6 GB | Too big | Get file → | |
| IQ4_XS | 17.9 GB | 20.4 GB | Too big | Get file → | |
| Q8_0 | 35.4 GB | 38.0 GB | Too big | Get file → |
What GPU do you need for CodeFuse DeepSeek 33B iMat?
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: the best quant that fits is IQ3_XXS (12.9 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is IQ4_XS (17.9 GB file, about 20.4 GB in use).
- 32 GB VRAM: the best quant that fits is IQ4_XS (17.9 GB file, about 20.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (35.4 GB file, about 38.0 GB in use).
Which CodeFuse DeepSeek 33B iMat quant should you choose?
IQ3_S (14.5 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 IQ3_XXS at 12.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about CodeFuse DeepSeek 33B iMat
How much VRAM does CodeFuse DeepSeek 33B iMat need?
About 17.1 GB at IQ3_S with an 8K context window. That is the 14.5 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 CodeFuse DeepSeek 33B iMat on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of CodeFuse DeepSeek 33B iMat GGUF?
It depends on the quant: IQ3_XXS is 12.9 GB, IQ3_XS is 13.6 GB, IQ3_S is 14.5 GB, IQ3_M is 15.0 GB, IQ4_XS is 17.9 GB, Q8_0 is 35.4 GB.
What context length does CodeFuse DeepSeek 33B iMat support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.1 GB at 8K and 4.2 GB at 16K.
Where can I download CodeFuse DeepSeek 33B iMat GGUF?
The files are on Hugging Face in the dranger003/CodeFuse-DeepSeek-33B-iMat.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 CodeFuse DeepSeek 33B iMat 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.