Nemotron-Cascade-2-30B-A3B needs about 31.3 GB of memory at Q4_K_M (a 23.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 20 quants, from 0.1 GB to 57.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.
Nemotron-Cascade-2-30B-A3B is a 31.6B-parameter Nemotron model in GGUF format, quantized by Mungert. Its trained context length is 1024K tokens. The repository has 20 quant files, from 0.1 GB to 57.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 7.5 GB | Tight | Get file → | |
| IQ4_NL | 17.8 GB | 25.3 GB | Too big | Get file → | |
| IQ3_XS | 17.9 GB | 25.4 GB | Too big | Get file → | |
| IQ3_XXS | 17.9 GB | 25.4 GB | Too big | Get file → | |
| IQ4_XS | 17.9 GB | 25.4 GB | Too big | Get file → | |
| IQ3_M | 17.9 GB | 25.4 GB | Too big | Get file → | |
| MXFP4_MOE | 18.0 GB | 25.5 GB | Too big | Get file → | |
| Q4_0 | 18.2 GB | 25.6 GB | Too big | Get file → | |
| Q3_K_S | 18.7 GB | 26.2 GB | Too big | Get file → | |
| Q4_1 | 19.8 GB | 27.3 GB | Too big | Get file → | |
| Q3_K_M | 20.2 GB | 27.7 GB | Too big | Get file → | |
| Q5_0 | 22.0 GB | 29.5 GB | Too big | Get file → | |
| Q4_K_S | 22.2 GB | 29.7 GB | Too big | Get file → | |
| Q4_K_M | 23.9 GB | 31.3 GB | Too big | Get file → | |
| Q5_1 | 23.9 GB | 31.4 GB | Too big | Get file → | |
| Q5_K_M | 27.2 GB | 34.7 GB | Too big | Get file → | |
| Q6_K_M | 33.5 GB | 41.0 GB | Too big | Get file → | |
| Q8_0 | 33.6 GB | 41.1 GB | Too big | Get file → | |
| BF16 | 57.1 GB (2 parts) | 64.6 GB | Too big | Get file → | |
| F16 | 57.1 GB (2 parts) | 64.6 GB | Too big | Get file → |
What GPU do you need for Nemotron-Cascade-2-30B-A3B?
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: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 7.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_1 (23.9 GB file, about 31.4 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (33.6 GB file, about 41.1 GB in use).
Which Nemotron-Cascade-2-30B-A3B quant should you choose?
Q4_K_M is the usual starting point for Nemotron-Cascade-2-30B-A3B: it balances file size and quality well. Here it is a 23.9 GB file.
The Q8_0 file is 33.6 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nemotron-Cascade-2-30B-A3B
How much VRAM does Nemotron-Cascade-2-30B-A3B need?
About 31.3 GB at Q4_K_M with an 8K context window. That is the 23.9 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 Nemotron-Cascade-2-30B-A3B on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nemotron-Cascade-2-30B-A3B GGUF?
It depends on the quant: file is 0.1 GB, IQ4_NL is 17.8 GB, IQ3_XS is 17.9 GB, IQ3_XXS is 17.9 GB, IQ4_XS is 17.9 GB, IQ3_M is 17.9 GB and 14 more.
What context length does Nemotron-Cascade-2-30B-A3B support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.0 GB at 8K and 27.9 GB at 32K.
Where can I download Nemotron-Cascade-2-30B-A3B GGUF?
The files are on Hugging Face in the Mungert/Nemotron-Cascade-2-30B-A3B-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 Nemotron-Cascade-2-30B-A3B 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.