nvidia.Cosmos Reason2 32B needs about 22.4 GB of memory at F16 (a 19.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 12.3 GB (F16) to 34.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
nvidia.Cosmos Reason2 32B is a 32.8B-parameter Cosmos model in GGUF format, quantized by DevQuasar. Its trained context length is 256K tokens. The repository has 6 quant files, from 12.3 GB (F16) to 34.8 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 12.3 GB | 15.0 GB | Too big | Get file → | |
| F16 | 16.0 GB | 18.6 GB | Too big | Get file → | |
| F16 | 19.8 GB | 22.4 GB | Too big | Get file → | |
| F16 | 23.2 GB | 25.9 GB | Too big | Get file → | |
| F16 | 26.9 GB | 29.5 GB | Too big | Get file → | |
| F16 | 34.8 GB | 37.5 GB | Too big | Get file → |
What GPU do you need for nvidia.Cosmos Reason2 32B?
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 F16 (12.3 GB file, about 15.0 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (19.8 GB file, about 22.4 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (26.9 GB file, about 29.5 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (34.8 GB file, about 37.5 GB in use).
Which nvidia.Cosmos Reason2 32B quant should you choose?
F16 (19.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is F16 at 12.3 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about nvidia.Cosmos Reason2 32B
How much VRAM does nvidia.Cosmos Reason2 32B need?
About 22.4 GB at F16 with an 8K context window. That is the 19.8 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 nvidia.Cosmos Reason2 32B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of nvidia.Cosmos Reason2 32B GGUF?
It depends on the quant: F16 is 12.3 GB, F16 is 16.0 GB, F16 is 19.8 GB, F16 is 23.2 GB, F16 is 26.9 GB, F16 is 34.8 GB.
What context length does nvidia.Cosmos Reason2 32B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download nvidia.Cosmos Reason2 32B GGUF?
The files are on Hugging Face in the DevQuasar/nvidia.Cosmos-Reason2-32B-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 nvidia.Cosmos Reason2 32B 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.