NorLlama 3B needs about 6.6 GB of memory at its main file (a 3.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 2.3 GB to 6.1 GB.
NorLlama 3B is a 3.07B-parameter Norllama model in GGUF format, quantized by MarsupialAI. Its trained context length is 2K tokens. The repository has 3 quant files, from 2.3 GB to 6.1 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.3 GB | 3.5 GB | Fits | Get file → | |
| — | 3.3 GB | 4.5 GB | Fits | Get file → | |
| — | 6.1 GB | 7.3 GB | Tight | Get file → |
What GPU do you need for NorLlama 3B?
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: the best quant that fits is the main file (2.3 GB file, about 5.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (3.3 GB file, about 6.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (6.1 GB file, about 9.5 GB in use).
Which NorLlama 3B quant should you choose?
If memory is tight, the smallest file is the first one in the table at 2.3 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 NorLlama 3B
How much VRAM does NorLlama 3B need?
About 6.6 GB at its main file with an 8K context window. That is the 3.3 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 NorLlama 3B on an 8 GB GPU?
Yes, with the smaller files: the 3.3 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of NorLlama 3B GGUF?
It depends on the quant: file is 2.3 GB, file is 3.3 GB, file is 6.1 GB.
What context length does NorLlama 3B support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.8 GB at 8K and 0.7 GB at 2K.
Where can I download NorLlama 3B GGUF?
The files are on Hugging Face in the MarsupialAI/NorLlama-3B_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 NorLlama 3B use?
Hugging Face lists the license as cc-by-nc-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.