aya23 needs about 23.2 GB of memory at its main file (a 20.2 GB file) with an 8K context window, so it fits on a 24 GB GPU.
aya23 is a 35B-parameter Aya model in GGUF format, quantized by della20241. Its trained context length is 8K tokens. The repository has 1 quant file, from 20.2 GB to 20.2 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 20.2 GB | 23.2 GB | Too big | Get file → |
What GPU do you need for aya23?
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 (20.2 GB file, about 23.2 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about aya23
How much VRAM does aya23 need?
About 23.2 GB at its main file with an 8K context window. That is the 20.2 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 aya23 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 23.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of aya23 GGUF?
It depends on the quant: file is 20.2 GB.
What context length does aya23 support?
The GGUF header lists a trained context length of 8,192 tokens (8K).
Where can I download aya23 GGUF?
The files are on Hugging Face in the della20241/aya23 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does aya23 use?
Hugging Face lists the license as gpl. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.