Kira needs about 15.2 GB of memory at its main file (a 13.1 GB file) with an 8K context window, so it fits on a 16 GB GPU.
Kira is a 20.4B-parameter Kira model in GGUF format, quantized by akimada. The repository has 1 quant file, from 13.1 GB to 13.1 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 13.1 GB | 15.2 GB | Too big | Get file → |
What GPU do you need for Kira?
These figures add the file size, an fp16 KV cache at an 8K context window 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 the main file (13.1 GB file, about 15.2 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about Kira
How much VRAM does Kira need?
About 15.2 GB at its main file with an 8K context window. That is the 13.1 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 Kira on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Kira GGUF?
It depends on the quant: file is 13.1 GB.
Where can I download Kira GGUF?
The files are on Hugging Face in the akimada/Kira repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.