onca 2.0 12b needs about 23.2 GB of memory at its main file (a 9.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 7.4 GB to 23.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 51.5 GB.
onca 2.0 12b is a 11.9B-parameter Gemma model in GGUF format, quantized by Joesh1. Its trained context length is 256K tokens. The repository has 4 quant files, from 7.4 GB to 23.8 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 7.4 GB | 20.8 GB | Too big | Get file → | |
| — | 9.8 GB | 23.2 GB | Too big | Get file → | |
| — | 12.7 GB | 26.1 GB | Too big | Get file → | |
| BF16 | 23.8 GB | 37.2 GB | Too big | Get file → |
What GPU do you need for onca 2.0 12b?
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: the best quant that fits is the main file (9.8 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (12.7 GB file, about 26.1 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (23.8 GB file, about 37.2 GB in use).
Which onca 2.0 12b quant should you choose?
If memory is tight, the smallest file is the first one in the table at 7.4 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 onca 2.0 12b
How much VRAM does onca 2.0 12b need?
About 23.2 GB at its main file with an 8K context window. That is the 9.8 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 onca 2.0 12b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of onca 2.0 12b GGUF?
It depends on the quant: file is 7.4 GB, file is 9.8 GB, file is 12.7 GB, BF16 is 23.8 GB.
What context length does onca 2.0 12b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 12.9 GB at 8K and 51.5 GB at 32K.
Where can I download onca 2.0 12b GGUF?
The files are on Hugging Face in the Joesh1/onca-2.0-12b-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 onca 2.0 12b 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.