nvidia_NVIDIA Nemotron 3 Nano 30B A3B FP8_local needs about 32.0 GB of memory at its main file (a 24.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.
nvidia_NVIDIA Nemotron 3 Nano 30B A3B FP8_local is a 31.6B-parameter Nemotron model in GGUF format, quantized by modelfix. Its trained context length is 1024K tokens. The repository has 1 quant file, from 24.5 GB to 24.5 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 24.5 GB | 32.0 GB | Too big | Get file → |
What GPU do you need for nvidia_NVIDIA Nemotron 3 Nano 30B A3B FP8_local?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is the main file (24.5 GB file, about 32.0 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about nvidia_NVIDIA Nemotron 3 Nano 30B A3B FP8_local
How much VRAM does nvidia_NVIDIA Nemotron 3 Nano 30B A3B FP8_local need?
About 32.0 GB at its main file with an 8K context window. That is the 24.5 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 nvidia_NVIDIA Nemotron 3 Nano 30B A3B FP8_local on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 32.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of nvidia_NVIDIA Nemotron 3 Nano 30B A3B FP8_local GGUF?
It depends on the quant: file is 24.5 GB.
What context length does nvidia_NVIDIA Nemotron 3 Nano 30B A3B FP8_local 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 nvidia_NVIDIA Nemotron 3 Nano 30B A3B FP8_local GGUF?
The files are on Hugging Face in the modelfix/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8-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_NVIDIA Nemotron 3 Nano 30B A3B FP8_local 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.