G2 Noranum 27B Q3 K S needs about 15.8 GB of memory at Q3_K_S (a 12.2 GB file) with an 8K context window, so it fits on a 16 GB GPU.
G2 Noranum 27B Q3 K S is a 27.2B-parameter Noranum model in GGUF format, quantized by djuna. Its trained context length is 8K tokens. The repository has 1 quant file, from 12.2 GB (Q3_K_S) to 12.2 GB (Q3_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 12.2 GB | 15.8 GB | Too big | Get file → |
What GPU do you need for G2 Noranum 27B Q3 K S?
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 Q3_K_S (12.2 GB file, about 15.8 GB in use).
Which G2 Noranum 27B Q3 K S quant should you choose?
Q3_K_S (12.2 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about G2 Noranum 27B Q3 K S
How much VRAM does G2 Noranum 27B Q3 K S need?
About 15.8 GB at Q3_K_S with an 8K context window. That is the 12.2 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 G2 Noranum 27B Q3 K S on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of G2 Noranum 27B Q3 K S GGUF?
It depends on the quant: Q3_K_S is 12.2 GB.
What context length does G2 Noranum 27B Q3 K S support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.
Where can I download G2 Noranum 27B Q3 K S GGUF?
The files are on Hugging Face in the djuna/G2-Noranum-27B-Q3_K_S-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.