krea2 base needs about 9.8 GB of memory at F16 (a 8.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 8.1 GB (F16) to 9.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
krea2 base is a 4.02B-parameter Krea model in GGUF format, quantized by fwwrsd. Its trained context length is 40K tokens. The repository has 2 quant files, from 8.1 GB (F16) to 9.5 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 8.1 GB | 9.8 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.2 GB | Too big | Get file → |
What GPU do you need for krea2 base?
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: the best quant that fits is Q8_0 (9.5 GB file, about 11.2 GB in use).
Which krea2 base quant should you choose?
F16 (8.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about krea2 base
How much VRAM does krea2 base need?
About 9.8 GB at F16 with an 8K context window. That is the 8.1 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 krea2 base on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of krea2 base GGUF?
It depends on the quant: F16 is 8.1 GB, Q8_0 is 9.5 GB.
What context length does krea2 base support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download krea2 base GGUF?
The files are on Hugging Face in the fwwrsd/krea2-base repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.