loras422 needs about 16.1 GB of memory at its main file (a 14.0 GB file) with an 8K context window, so it fits on a 24 GB GPU.
loras422 is a 12.8B-parameter Loras model in GGUF format, quantized by martineux. The repository has 1 quant file, from 14.0 GB to 14.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.0 GB | 16.1 GB | Too big | Get file → |
What GPU do you need for loras422?
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: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is the main file (14.0 GB file, about 16.1 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about loras422
How much VRAM does loras422 need?
About 16.1 GB at its main file with an 8K context window. That is the 14.0 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 loras422 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of loras422 GGUF?
It depends on the quant: file is 14.0 GB.
Where can I download loras422 GGUF?
The files are on Hugging Face in the martineux/loras422 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.