cosmos needs about 5.1 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 3.1 GB (Q3_K_M) to 5.0 GB (Q5_K_M).
cosmos is a 7.24B-parameter Cosmos model in GGUF format, quantized by calcuis. The repository has 3 quant files, from 3.1 GB (Q3_K_M) to 5.0 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 3.1 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 4.1 GB | 5.1 GB | Fits | Get file → | |
| Q5_K_M | 5.0 GB | 6.1 GB | Fits | Get file → |
What GPU do you need for cosmos?
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_M (3.1 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_K_M (4.1 GB file, about 5.1 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.0 GB file, about 6.1 GB in use).
Which cosmos quant should you choose?
Q4_K_M is the usual starting point for cosmos: it balances file size and quality well. Here it is a 4.1 GB file.
If memory is tight, the smallest file is Q3_K_M at 3.1 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
Source
Frequently asked questions about cosmos
How much VRAM does cosmos need?
About 5.1 GB at Q4_K_M with an 8K context window. That is the 4.1 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 cosmos on an 8 GB GPU?
Yes, with Q5_K_M: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of cosmos GGUF?
It depends on the quant: Q3_K_M is 3.1 GB, Q4_K_M is 4.1 GB, Q5_K_M is 5.0 GB.
Where can I download cosmos GGUF?
The files are on Hugging Face in the calcuis/cosmos repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does cosmos 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.