migtissera DeepSeek Coder V2 Base needs about 114.4 GB of memory at IQ3_S (a 101.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 11 quants, from 0.0 GB (Q3_K_L) to 133.9 GB (Q4_K_S).
migtissera DeepSeek Coder V2 Base is a 230B-parameter DeepSeek model in GGUF format, quantized by RichardErkhov. The repository has 11 quant files, from 0.0 GB (Q3_K_L) to 133.9 GB (Q4_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_S | 61.8 GB (2 parts) | 69.7 GB | Too big | Get file → | |
| Q2_K | 85.9 GB (3 parts) | 96.8 GB | Too big | Get file → | |
| Q4_0 | 86.8 GB (3 parts) | 97.7 GB | Too big | Get file → | |
| IQ3_XS | 96.3 GB (3 parts) | 108.4 GB | Too big | Get file → | |
| IQ3_S | 101.7 GB (3 parts) | 114.4 GB | Too big | Get file → | |
| IQ3_M | 103.4 GB (3 parts) | 116.3 GB | Too big | Get file → | |
| Q3_K | 112.7 GB (3 parts) | 126.7 GB | Too big | Get file → | |
| IQ4_XS | 126.8 GB (4 parts) | 142.5 GB | Too big | Get file → | |
| IQ4_NL | 133.9 GB (4 parts) | 150.4 GB | Too big | Get file → | |
| Q4_K_S | 133.9 GB (4 parts) | 150.4 GB | Too big | Get file → |
What GPU do you need for migtissera DeepSeek Coder V2 Base?
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: the best quant that fits is Q3_K_L (0.0 GB file, about 0.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q3_K_L (0.0 GB file, about 0.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q3_K_L (0.0 GB file, about 0.5 GB in use).
- 12 GB VRAM: the best quant that fits is Q3_K_L (0.0 GB file, about 0.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q3_K_L (0.0 GB file, about 0.5 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K_L (0.0 GB file, about 0.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q3_K_L (0.0 GB file, about 0.5 GB in use).
- 48 GB VRAM: the best quant that fits is Q3_K_L (0.0 GB file, about 0.5 GB in use).
Which migtissera DeepSeek Coder V2 Base quant should you choose?
IQ3_S (101.7 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 Q3_K_L at 0.0 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 migtissera DeepSeek Coder V2 Base
How much VRAM does migtissera DeepSeek Coder V2 Base need?
About 114.4 GB at IQ3_S with an 8K context window. That is the 101.7 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 migtissera DeepSeek Coder V2 Base on an 8 GB GPU?
Yes, with Q3_K_L: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of migtissera DeepSeek Coder V2 Base GGUF?
It depends on the quant: Q3_K_L is 0.0 GB, Q3_K_S is 61.8 GB, Q2_K is 85.9 GB, Q4_0 is 86.8 GB, IQ3_XS is 96.3 GB, IQ3_S is 101.7 GB and 5 more.
Where can I download migtissera DeepSeek Coder V2 Base GGUF?
The files are on Hugging Face in the RichardErkhov/migtissera_-_DeepSeek-Coder-V2-Base-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.