aria v20 needs about 6.1 GB of memory at its main file (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU.
aria v20 is a 8.19B-parameter Aria model in GGUF format, quantized by speri420. Its trained context length is 128K tokens. The repository has 1 quant file, from 5.0 GB to 5.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 5.0 GB | 6.1 GB | Fits | Get file → |
What GPU do you need for aria v20?
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: the best quant that fits is the main file (5.0 GB file, about 6.1 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about aria v20
How much VRAM does aria v20 need?
About 6.1 GB at its main file with an 8K context window. That is the 5.0 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 aria v20 on an 8 GB GPU?
Yes, with the smaller files: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of aria v20 GGUF?
It depends on the quant: file is 5.0 GB.
What context length does aria v20 support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download aria v20 GGUF?
The files are on Hugging Face in the speri420/aria-v20 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.