NBE gemma 3 needs about 1.8 GB of memory at its main file (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
NBE gemma 3 is a 1B-parameter Gemma model in GGUF format, quantized by Omarwalid96. Its trained context length is 32K tokens. The repository has 1 quant file, from 1.1 GB to 1.1 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.1 GB | 1.8 GB | Fits | Get file → |
What GPU do you need for NBE gemma 3?
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: the best quant that fits is the main file (1.1 GB file, about 1.8 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about NBE gemma 3
How much VRAM does NBE gemma 3 need?
About 1.8 GB at its main file with an 8K context window. That is the 1.1 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 NBE gemma 3 on an 8 GB GPU?
Yes, with the smaller files: the 1.1 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NBE gemma 3 GGUF?
It depends on the quant: file is 1.1 GB.
What context length does NBE gemma 3 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download NBE gemma 3 GGUF?
The files are on Hugging Face in the Omarwalid96/NBE-gemma-3 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does NBE gemma 3 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.